Transfer Optimisation System for Adaptive Automated Nature-Inspired Optimisation
Lead Research Organisation:
UNIVERSITY OF EXETER
Department Name: Computer Science
Abstract
Hard optimisation problems are ubiquitous across the breadth of science, engineering and economics. For example, in water system planning and management, water companies are often interested in optimising several system performance measures of their infrastructures in order to provide sustainable and resilient water/wastewater services that are able to cope with and recover from disruption, as well as wider challenges brought by climate change and population increase. As a classic discipline, significant advances in both theory and algorithms have been achieved in optimisation. However, almost all traditional optimisation solvers, ranging from classic methods to nature-inspired computational intelligence techniques, ignore some important facts: (i) real-world optimisation problems seldom exist in isolation; and (ii) artificial systems are designed to tackle a large number of problems over their lifetime, many of which are repetitive or inherently related. Instead, optimisation is run as a 'one-off' process, i.e. it is started from scratch by assuming zero prior knowledge each time. Therefore, knowledge/experience from solving different (but possibly related) optimisation exercises (either previously completed or currently underway), which can be useful for enhancing the target optimisation task at hand, will be wasted. Although the Bayesian optimisation considers incorporating some decision maker's knowledge as a prior, the gathered experience during the optimisation process is discarded afterwards. In this case, we cannot expect any automatic growth of their capability with experience. This practice is counter-intuitive from the cognitive perspective where humans routinely grow from a novice to domain experts by gradually accumulating problem-solving experience and making use of existing knowledge to tackle new unseen tasks. In machine learning, leveraging knowledge gained from related source tasks to improve the learning of the new task is known as transfer learning, an emerging field that considerable success has been witnessed in a wide range of application domains. There have been some attempts on applying transfer learning in evolutionary computation, but they do not consider the optimisation as a closed-loop system. Moreover, the recurrent patterns within problem-solving exercises have been discarded after optimisation, thus experience cannot be accumulated over time.
The proposed research will develop a revolutionary general-purpose optimiser (as known as transfer optimisation system) that will be able to learn knowledge/experience from previous optimisation process and then autonomously and selectively transfer such knowledge to new unseen optimisation tasks. The transfer optimisation system places adaptive automation at the heart of the development process and explores novel synergies at the crossroads of several disciplines including nature-inspired computation, machine learning, human-computer interaction and high-performance parallel computing. The outputs will bring automation in industry, including an optimised/shortened production cycle, reduced resource consumption and more balanced and innovative products, which have great potentials to result in economic savings and an increase of turnover. The proposed methods will be rigorously evaluated by the industrial partners, first in water industry and will be expanded to a boarder range of sectors which put the optimisation at the heart of their regular production/management process (e.g. renewable energy, healthcare, automotive, appliance and medicine manufacturers).
The proposed research will develop a revolutionary general-purpose optimiser (as known as transfer optimisation system) that will be able to learn knowledge/experience from previous optimisation process and then autonomously and selectively transfer such knowledge to new unseen optimisation tasks. The transfer optimisation system places adaptive automation at the heart of the development process and explores novel synergies at the crossroads of several disciplines including nature-inspired computation, machine learning, human-computer interaction and high-performance parallel computing. The outputs will bring automation in industry, including an optimised/shortened production cycle, reduced resource consumption and more balanced and innovative products, which have great potentials to result in economic savings and an increase of turnover. The proposed methods will be rigorously evaluated by the industrial partners, first in water industry and will be expanded to a boarder range of sectors which put the optimisation at the heart of their regular production/management process (e.g. renewable energy, healthcare, automotive, appliance and medicine manufacturers).
Planned Impact
This programme of research will create a revolutionary computational search framework. It opens a systematic and rational avenue to the design and analysis of computational search methodologies (evolutionary computation in particular). In the long term, it has significant impact to a broader spectrum of computational intelligence, meta-heuristics, operational research (OR) and even traditional optimisation. At the broadest level, this research explores novel synergies among nature-inspired computation, machine learning, human-computer interaction and high-performance parallel computing, which create strong ties among several EPSRC portfolios (Artificial Intelligence Technology, OR, human-computer interaction) and will address the Cross Information and Communications Technology (ICT) Programme Priority 'Cross-Disciplinarily and Co-Creation' and UKRI cross-organisational themes and programmes. Furthermore, it also addresses other 3 out of the 6 ICT Programme Priorities (none can address all six). Specifically, as the proposed methods place adaptive automation at the heart of the development process, it is directly relevant to the Priority 'Future Intelligent Technologies'. As the domain knowledge from human expertise can be selectively transferred for accelerating new optimisation tasks, thus realising human-in-the-loop, this research will be highly relevant to the Priorities 'People at the Heat of ICT'. Furthermore, data mining and knowledge discovery upon optimised solutions and innovization will address the Priority 'Data Enabled Decision Making'.
This research will directly impact the optimal water system planning and management, which will provide resilient, safe, reliable, and efficient operations for future UK water companies. Furthermore, the programme of research is directly relevant to the government's Industry Strategy, since cost-effective, adaptive computational search is critical to many applications that underpin the Industry Challenge. For example, it is important in tackling challenges in 'Manufacturing and Future Materials' such as the design of light-weight composite materials and managing sustainability across manufacturing systems. Optimisation of complex systems is important to the 'Transforming Construction', 'Prospering from the Energy Revolution' and Clean Growth, e.g., smart building deployments, renewable energy devices. In 'Leading-edge Healthcare', optimisation is essential to accelerate new drug discovery and the improvement of diagnostic tools.
The pathways to impact can be summarised as:
Ensuring academic impacts: (i) present research results at major international conferences in the evolutionary computation, artificial intelligence fields; (ii) publish research results at prestigious international journals; and (iii) organise workshops and disseminate tutorials associated with major conferences to foster an active state of the investigated programme.
Engaging with industries: (i) organise four industry-focused workshops in Exeter to reach out companies who are interested in advanced optimisation techniques in their regular production/operation process, and engage them as research partners to develop case studies; (ii) actively seek opportunities for commercial exploitation of the research outcomes and engage University's Innovation, Impact and Business whenever appropriate; and (iii) offer free technical consultancy on cutting-edge optimisation techniques for a limited period (typically 1-2 days) to SMEs mainly in the south west region.
Engaging with general public: (i) collaborate with the University's Outreach team to host summer schools; and (ii) deliver demonstrations, presentations about research and impacts at University open days.
People and knowledge: (i) PDRAs will gain practical leadership and project management skills by co-supervising PhD students; (ii) research results will be used as study materials in taught undergraduate/postgraduate level modules.
This research will directly impact the optimal water system planning and management, which will provide resilient, safe, reliable, and efficient operations for future UK water companies. Furthermore, the programme of research is directly relevant to the government's Industry Strategy, since cost-effective, adaptive computational search is critical to many applications that underpin the Industry Challenge. For example, it is important in tackling challenges in 'Manufacturing and Future Materials' such as the design of light-weight composite materials and managing sustainability across manufacturing systems. Optimisation of complex systems is important to the 'Transforming Construction', 'Prospering from the Energy Revolution' and Clean Growth, e.g., smart building deployments, renewable energy devices. In 'Leading-edge Healthcare', optimisation is essential to accelerate new drug discovery and the improvement of diagnostic tools.
The pathways to impact can be summarised as:
Ensuring academic impacts: (i) present research results at major international conferences in the evolutionary computation, artificial intelligence fields; (ii) publish research results at prestigious international journals; and (iii) organise workshops and disseminate tutorials associated with major conferences to foster an active state of the investigated programme.
Engaging with industries: (i) organise four industry-focused workshops in Exeter to reach out companies who are interested in advanced optimisation techniques in their regular production/operation process, and engage them as research partners to develop case studies; (ii) actively seek opportunities for commercial exploitation of the research outcomes and engage University's Innovation, Impact and Business whenever appropriate; and (iii) offer free technical consultancy on cutting-edge optimisation techniques for a limited period (typically 1-2 days) to SMEs mainly in the south west region.
Engaging with general public: (i) collaborate with the University's Outreach team to host summer schools; and (ii) deliver demonstrations, presentations about research and impacts at University open days.
People and knowledge: (i) PDRAs will gain practical leadership and project management skills by co-supervising PhD students; (ii) research results will be used as study materials in taught undergraduate/postgraduate level modules.
Organisations
- UNIVERSITY OF EXETER (Fellow, Lead Research Organisation)
- University of Technology Sydney (Collaboration)
- Hong Kong Polytechnic University (Collaboration)
- Leiden University (Collaboration)
- John Innes Centre (Collaboration)
- University of Warwick (Collaboration)
- Amazon.com (Collaboration)
- Dashboard (United Kingdom) (Project Partner)
- Western Provident Association (Project Partner)
- Pennon Group (United Kingdom) (Project Partner)
Publications
Lyu B
(2023)
Efficient Spectral Graph Convolutional Network Deployment on Memristive Crossbars
in IEEE Transactions on Emerging Topics in Computational Intelligence
Wu J
(2022)
Distributed UAV Swarm Formation and Collision Avoidance Strategies Over Fixed and Switching Topologies.
in IEEE transactions on cybernetics
Wu M
(2020)
Evolutionary Many-Objective Optimization Based on Adversarial Decomposition.
in IEEE transactions on cybernetics
Dendir S
(2022)
Race, ethnicity and mortality in the United States during the first year of the COVID-19 pandemic: an assessment.
in Discover social science and health
Lyu B
(2023)
MTLP-JR: Multi-task learning-based prediction for joint ranking in neural architecture search
in Computers and Electrical Engineering
Yang L
(2021)
A vector angles-based many-objective particle swarm optimization algorithm using archive
in Applied Soft Computing
Description | We developed new statistical methods to analyze the fitness landscapes of various combinatorial optimization problems. From our analysis, we are exciting to find the existence of structural similarity among different problems. In addition, we developed a life-long learning paradigm that implements a continuous learning with time and a self-adaptivity for newly incoming tasks. In 2021, we have developed a software product, dubbed DaNuoYi, that is able to automatically generate test inputs for multiple types of injection attacks on Web application firewalls. |
Exploitation Route | Our findings on structural similarity lay the foundation for transfer learning and optimization among different problems. Our DaNuoYi has shown the effectiveness of transfer learning and multi-tasking for solving challenging problems collaboratively. |
Sectors | Digital/Communication/Information Technologies (including Software) |
Description | One of our research outcome is a collaboration with Amazon AWS. We developed a new transfer learning driven test case generation tool to help identify vulnerabilities in the Web firewalls. This software product is going to be patented in 2023. |
First Year Of Impact | 2023 |
Sector | Digital/Communication/Information Technologies (including Software) |
Impact Types | Economic |
Description | Evolutionary Multi-Objective Search for Automating CNN Architecture Design |
Amount | £11,815 (GBP) |
Funding ID | IES\R2\212077 |
Organisation | The Royal Society |
Sector | Charity/Non Profit |
Country | United Kingdom |
Start | 11/2021 |
End | 10/2023 |
Description | Knowledge Representation in Transfer Optimisation System and Applications for Highly Configurable Software Systems |
Amount | £74,000 (GBP) |
Funding ID | 2404317 |
Organisation | Engineering and Physical Sciences Research Council (EPSRC) |
Sector | Public |
Country | United Kingdom |
Start | 09/2020 |
End | 03/2024 |
Description | Many Hands Make Work Light: Multi-task Deep Semantic Learning for Testing Web Application Firewalls |
Amount | $80,000 (USD) |
Organisation | Amazon.com |
Sector | Private |
Country | United States |
Start | 03/2021 |
End | 04/2022 |
Description | Towards Scalable Multi-Objective Bilevel Optimization: Foundations, Methodologies and Applications |
Amount | HK$1,150,000 (HKD) |
Funding ID | 11211521 |
Organisation | University Grants Committee |
Sector | Public |
Country | China |
Start | 08/2021 |
End | 08/2024 |
Description | Transfer Bayesian Optimization for Multi-Fidelity Data in Uncertain Environments |
Amount | £7,440 (GBP) |
Funding ID | GP ENF5.10 |
Organisation | European Commission |
Sector | Public |
Country | European Union (EU) |
Start | 07/2021 |
End | 07/2022 |
Description | Turing Fellowship |
Amount | £0 (GBP) |
Organisation | Alan Turing Institute |
Sector | Academic/University |
Country | United Kingdom |
Start | 08/2021 |
End | 08/2022 |
Description | Research collaboration with Dr Hatef Sadeghi in University of Warwick |
Organisation | University of Warwick |
Department | School of Engineering |
Country | United Kingdom |
Sector | Academic/University |
PI Contribution | We are collaborating with Dr Hatef Sadeghi in University of Warwick to work at a cutting-edge topic of using artificial intelligence tools to accelerate material discovery process. In particular, we are using machine learning techniques to learn latent patterns from the structural data of molecules. |
Collaborator Contribution | Dr Hatef Sadeghi is an expert in material science and he provides his expertise to identify important and challenging problems in his area. |
Impact | This is a multi-disciplinary collaboration between computer science and material science. We are going to develop some pilot research results that lead to publications at first and research funding afterwards. |
Start Year | 2019 |
Description | Research collaboration with Dr Yiliang Ding in John Innes Centre |
Organisation | John Innes Centre |
Country | United Kingdom |
Sector | Academic/University |
PI Contribution | My research team is collaborating with Dr Ding's group on using cutting edge artificial intelligence technologies to understand complex features embedded in RNA secondary structure. In addition, we aim to further the understanding to generate new techniques for RNA design. |
Collaborator Contribution | Dr Ding's group is one of the most active groups in the Europe working on the RNA structure analysis and identification. Dr Ding provides her expertise on biology and provides first hand data which are complex. |
Impact | This collaboration is multi-disciplinary between computer science and biology. We are on the process of collaboration and further results will be reported later this year. |
Start Year | 2020 |
Description | Research collaboration with Dr. Hao Wang in Leiden University, the Netherlands |
Organisation | Leiden University |
Country | Netherlands |
Sector | Academic/University |
PI Contribution | We organized a one-day symposium to connect the PhD students and postdoc researchers between my research team in Exeter and Dr Wang's group in Leiden. |
Collaborator Contribution | Dr Wang's group is one of the largest and the most active in the Europe for research on evolutionary computation and data-driven optimization. He and his group plans to organize the second symposium to invite my research team to visit Leiden in July for an in-depth discussion our collaborative bid for a COST Action in EU. |
Impact | The outputs of this collaboration are in two aspects. One is a link grant awarded by a European Network Fund (GP ENF5.10); while the other is mainly in the form of symposiums that connect the staffs, postodc researchers and PhD students together. This collaboration is currently within the computer science domain. But we are going to involve researchers in synthetic biology and quantum physics for a multi-disciplinary collaboration. |
Start Year | 2021 |
Description | Research collaboration with Prof. Kay Chen Tan in The Hong Kong Polytechnic University |
Organisation | Hong Kong Polytechnic University |
Country | Hong Kong |
Sector | Academic/University |
PI Contribution | We collaborate with Prof. Tan's research team on developing data-driven optimization techniques for large-scale bilevel optimization problems. We have started student exchange since 2020 between our two sides. In 2021, we have collaborated on a competitive research grant bit from Hong Kong GRF and it was successfully secured. |
Collaborator Contribution | Prof. Tan's research team is one of the most active research group in Asian on evolutionary computation and its applications. He and his team have been actively promoting the collaborative research on the large-scale bilevel optimization. |
Impact | The outputs are in two aspects. One is a successful competitive research grant application from Hong Kong GRF (11211521); the other is in the format of collaborative research including student exchange and collaborative papers. |
Start Year | 2020 |
Description | Research collaboration with Prof. Shiping Wen in University of Technology Sydney, Australia |
Organisation | University of Technology Sydney |
Country | Australia |
Sector | Academic/University |
PI Contribution | We have a pilot research work with Prof. Wen's research team in UTS on neural architecture search. The output is published as a journal paper in IEEE Transactions on Neural Networks and Learning Systems, a top-tier journal in the neural networks. |
Collaborator Contribution | They contribute some bespoke face recognition dataset collected in Prof. Wen's research team. This dataset has been used as a foundation in our collaborative project. |
Impact | There are two types of outputs. One is the collaborative papers (one is already published in IEEE Transactions on Neural Networks and Learning Systems, a top-tier journal in the neural networks); the other is a collaborative grant awarded from Royal Society (IES\R2\212077). This collaboration is not multi-disciplinary. |
Start Year | 2021 |
Description | Research collaboration with Prof. Willem Visser in Amazon AWS, USA |
Organisation | Amazon.com |
Department | Amazon Web Services |
Country | United States |
Sector | Private |
PI Contribution | We collaborate with Prof. Willem's team in Amazon AWS under the support of an Amazon Research Award. This project consists of three major tasks - gathering dataset for WAF profiling; develop a language model using multi-task learning that translates the test cases between any pair of injection attacks; and developing a multi-task evolutionary test case generator that co-evolve different types of injection attacks. |
Collaborator Contribution | Prof. Willem's team is active on research and innovation on static analysis and Web security. He and his team provide professional support and advise on the direction of this project. |
Impact | The outputs of this project are two folds. One is a prestigious Amazon Research Award; and the other is in the form of collaborative papers and software products. This project is not multi-disciplinary. |
Start Year | 2021 |
Title | DaNuoYi: Evolutionary Multitask Injection Generation Tool |
Description | Web application firewall (WAF) plays an integral role nowadays to protect web applications from various malicious injection attacks such as SQL injection, XML injection, and PHP injection, to name a few. However, given the evolving sophistication of injection attacks and the increasing complexity of tuning a WAF, it is challenging to ensure that the WAF is free of injection vulnerabilities such that it will block all malicious injection attacks without wrongly affecting the legitimate message. Automatically testing the WAF is, therefore, a timely and essential task. In this paper, we propose DaNuoYi, an automatic injection testing tool that simultaneously generates test inputs for multiple types of injection attacks on WAF. Our basic idea derives from the cross-lingual translation in natural language processing domain. In particular, test inputs for different types of injection attacks are syntactically different but may be semantically similar. Sharing semantic knowledge across multiple programming languages can thus stimulate the generation of more sophisticated test inputs and discovering injection vulnerabilities of the WAF that are otherwise difficult to find. To this end, in DaNuoYi, we train several injection translation models using multi-task learning that translates the test inputs between any pair of injection attacks. The model is then used by a novel multi-task evolutionary algorithm to co-evolve test inputs for different types of injection attacks facilitated by a shared mating pool and domain-specific mutation operators at each generation. We conduct experiments on three real-world open-source WAFs and six types of injection attacks, the results reveal that DaNuoYi generates up to 2.9x and 5.4x more valid test inputs (i.e., bypassing the underlying WAF) than its state-of-the-art single-task counterpart and the context-free grammar-based injection construction. |
Type Of Technology | Software |
Year Produced | 2021 |
Open Source License? | Yes |
Impact | This product is a product under the support of an Amazon Research Award. |
URL | https://github.com/COLA-Laboratory/DaNuoYi |
Title | EMOC: Evolutionary Multi-Objective Optimization Algorithm Package in C |
Description | This is the first algorithm package for evolutionary multi-objective optimization (EMO) written in C programming language. It contains more than 40 state-of-the-art EMO algorithms in the literature. In addition, it consists more than 70 benchmark test problems along with 5 different performance metrics. |
Type Of Technology | Systems, Materials & Instrumental Engineering |
Year Produced | 2020 |
Open Source License? | Yes |
Impact | This software has attracted 8 stars in Github and it facilitate the research and education in evolutionary multi-objective optimization. |
URL | https://github.com/COLA-Laboratory/EMOC |
Description | "Quo Vadis" Lecture Series in ECOLE ITN at the University of Birmingham |
Form Of Engagement Activity | Participation in an activity, workshop or similar |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Postgraduate students |
Results and Impact | More than 50 postgraduate students from the UK, Netherlands, Germany and China attended for this lecture series. Experience of growing from a PhD student to a principle investigator is shared with the attendants, which sparked questions and discussion afterwards. |
Year(s) Of Engagement Activity | 2021 |
Description | 110 minutes Tutorial at the 2021 IEEE Symposium Series on Computational Intelligence |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Postgraduate students |
Results and Impact | Around 40 researchers across the world attended for this 110 minutes tutorial at the 2021 IEEE Symposium Series on Computational Intelligence. This tutorial is about Decomposition Multi-Objective Optimisation: Current Developments and Future Opportunities. Within this tutorial, a comprehensive introduction to MOEA/D were given and selected research results will be presented in more detail. More specifically, it (i) introduced the basic principles of MOEA/D in comparison with other two state-of-the-art EMO frameworks, i.e., Pareto- and indicator-based frameworks; (ii) presented a general overview of state-of-the-art MOEA/D variants and their applications; (iii) discussed the future opportunities for possible further developments. |
Year(s) Of Engagement Activity | 2021 |
URL | https://attend.ieee.org/ssci-2021/tutorial-decomposition-multi-objective-optimization-current-develo... |
Description | 110 minutes Tutorial at the 20th Annual Conference on Genetic and Evolutionary Computation |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Other audiences |
Results and Impact | More than 60 researchers across the world attended for this 110 minutes tutorial at the 20th Annual Conference on Genetic and Evolutionary Computation. This tutorial is about Decomposition Multi-Objective Optimisation: Current Developments and Future Opportunities. Within this tutorial, a comprehensive introduction to MOEA/D were given and selected research results will be presented in more detail. More specifically, it (i) introduced the basic principles of MOEA/D in comparison with other two state-of-the-art EMO frameworks, i.e., Pareto- and indicator-based frameworks; (ii) presented a general overview of state-of-the-art MOEA/D variants and their applications; (iii) discussed the future opportunities for possible further developments. |
Year(s) Of Engagement Activity | 2019 |
URL | https://gecco-2019.sigevo.org/index.html/Tutorials#id_Decomposition%20Multi-Objective%20Optimization... |
Description | 110 minutes Tutorial at the 21th Annual Conference on Genetic and Evolutionary Computation |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Other audiences |
Results and Impact | More than 70 researchers across the world attended for this 110 minutes tutorial at the 21th Annual Conference on Genetic and Evolutionary Computation. This tutorial is about Decomposition Multi-Objective Optimisation: Current Developments and Future Opportunities. Within this tutorial, a comprehensive introduction to MOEA/D were given and selected research results will be presented in more detail. More specifically, it (i) introduced the basic principles of MOEA/D in comparison with other two state-of-the-art EMO frameworks, i.e., Pareto- and indicator-based frameworks; (ii) presented a general overview of state-of-the-art MOEA/D variants and their applications; (iii) discussed the future opportunities for possible further developments. |
Year(s) Of Engagement Activity | 2020 |
URL | https://gecco-2020.sigevo.org/index.html/Tutorials#id_Decomposition%20Multi-Objective%20Optimisation... |
Description | 110 minutes Tutorial at the 22nd Annual Conference on Genetic and Evolutionary Computation |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Postgraduate students |
Results and Impact | More than 70 researchers across the world attended for this 110 minutes tutorial at the 22nd Annual Conference on Genetic and Evolutionary Computation. This tutorial is about Decomposition Multi-Objective Optimisation: Current Developments and Future Opportunities. Within this tutorial, a comprehensive introduction to MOEA/D were given and selected research results will be presented in more detail. More specifically, it (i) introduced the basic principles of MOEA/D in comparison with other two state-of-the-art EMO frameworks, i.e., Pareto- and indicator-based frameworks; (ii) presented a general overview of state-of-the-art MOEA/D variants and their applications; (iii) discussed the future opportunities for possible further developments. |
Year(s) Of Engagement Activity | 2021 |
URL | https://gecco-2021.sigevo.org/Tutorials#id_Decomposition%20Multi-Objective%20Optimization:%20Current... |
Description | 90 minutes Tutorial at the 16th International Conference on Parallel Problem Solving from Nature |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Other audiences |
Results and Impact | More than 60 researchers across the world attended for this tutorial at the 16th International Conference on Parallel Problem Solving from Nature. This tutorial (i) introduced the basic principles of MOEA/D in comparison with other two state-of-the-art EMO frameworks, i.e., Pareto- and indicator-based frameworks; (ii) presented a general overview of state-of-the-art MOEA/D variants and their applications; (iii) discussed opportunities for further exploration. |
Year(s) Of Engagement Activity | 2020,2022 |
Description | Founding chair of Task Force on Decomposition-based Techniques in Evolutionary Computation in IEEE Computational Intelligence Society |
Form Of Engagement Activity | A formal working group, expert panel or dialogue |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Other audiences |
Results and Impact | This is an international consortium to bring researchers across the world together to focus and promote the development of decomposition techniques in evolutionary computation. There are more than 20 active members in this IEEE task force. In addition, workshops, seminars and special issues are developed regularly to promote the related research theme. |
Year(s) Of Engagement Activity | 2019,2020,2021 |
URL | https://cola-laboratory.github.io/docs/misc/dtec/ |
Description | Give a 110 mins tutorial in 2022 IEEE SSCI |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Policymakers/politicians |
Results and Impact | Around 40 researchers across the world attended for this 110 minutes tutorial at the 2022 IEEE Symposium Series on Computational Intelligence. This tutorial is about Decomposition Multi-Objective Optimisation: Current Developments and Future Opportunities. Within this tutorial, a comprehensive introduction to MOEA/D were given and selected research results will be presented in more detail. More specifically, it (i) introduced the basic principles of MOEA/D in comparison with other two state-of-the-art EMO frameworks, i.e., Pareto- and indicator-based frameworks; (ii) presented a general overview of state-of-the-art MOEA/D variants and their applications; (iii) discussed the future opportunities for possible further developments. |
Year(s) Of Engagement Activity | 2022 |
URL | https://ieeessci2022.org/tutorial-schedule.html |
Description | Give a 90 mins tutorial in PPSN 2022 |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Professional Practitioners |
Results and Impact | More than 60 researchers across the world attended for this tutorial at the 17th International Conference on Parallel Problem Solving from Nature. This tutorial (i) introduced the basic principles of MOEA/D in comparison with other two state-of-the-art EMO frameworks, i.e., Pareto- and indicator-based frameworks; (ii) presented a general overview of state-of-the-art MOEA/D variants and their applications; (iii) discussed opportunities for further exploration. |
Year(s) Of Engagement Activity | 2022 |
URL | https://ppsn2022.cs.tu-dortmund.de/ |
Description | IEEE Computational Intelligence Society Summer School |
Form Of Engagement Activity | Participation in an activity, workshop or similar |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Postgraduate students |
Results and Impact | More than 200 people (including undergraduate, PhD students, postdoc researchers, industry partners from the UK, China, USA, Australia, Italy, France and Germany) attended this summer school. There are four high-profile keynote speeches, two tutorials and eight invited talks in this summer school. The attendees are very active and showed strong interests in the topics. |
Year(s) Of Engagement Activity | 2021 |
URL | https://sites.google.com/view/ss-ddaci/home |
Description | Join the GREAT Talent campaign hosted by the Cabinet Office |
Form Of Engagement Activity | A press release, press conference or response to a media enquiry/interview |
Part Of Official Scheme? | No |
Geographic Reach | National |
Primary Audience | Media (as a channel to the public) |
Results and Impact | I was invited to join an interview activity hosted by The UKRI Global Mobility Team, Cabinet Office and the Office for Talent to showcase a video interview. The goal of this event is to promote the UK as a leading location for Research and Innovation and to make the process of relocating easier. |
Year(s) Of Engagement Activity | 2022 |
URL | https://greattalent.campaign.gov.uk/work-in-the-uk/ |
Description | Publication Chair of the 11th International Conference on Evolutionary Multi-Criterion Optimization in Shenzhen, China |
Form Of Engagement Activity | Participation in an activity, workshop or similar |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Postgraduate students |
Results and Impact | This is the most important academic event in the evolutionary multi-objective optimization community. Due to the COVID-19 pandemic, this event is hosted in a hybrid style with most attendees are online while some researchers from China can participate in person. There are more than 400 researchers across the world register this conference. In total there are around 170 papers got accepted and being presented during the conference. |
Year(s) Of Engagement Activity | 2021 |
URL | https://emo2021.org/ |