About
66
Publications
4,021
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
264
Citations
Publications
Publications (66)
Schema, a form of structured knowledge that promotes transfer learning, is attracting growing attention in both neuroscience and artificial intelligence (AI). Current schema research in neural computation is largely constrained to a single behavioral paradigm and relies heavily on recurrent neural networks (RNNs) which lack the neural plausibility...
This manuscript considers distributed optimization problems in systems with cooperative-collaborative relationships, involving two groups of nodes, each with its own optimization problem, but with a coupled communication topology. For the signed graph representing the cooperation and collaboration between agents, this manuscript introduces DIG-JOR,...
Feature Generative Adversarial Networks have emerged as powerful generative models in producing high-quality representations of unseen classes within the scope of Zero-shot Learning (ZSL). This paper delves into the pivotal influence of unseen class priors within the framework of transductive ZSL (TZSL) and illuminates the finding that even a margi...
Multi-agent hierarchical reinforcement learning (MAHRL) has been studied as an effective means to solve intelligent decision problems in complex and large-scale environments. However, most current MAHRL algorithms follow the traditional way of using reward functions in reinforcement learning, which limits their use to a single task. This study aims...
Large Language Models (LLMs) such as OpenAI’s ChatGPT have achieved surprisingly huge progresses in the field of Natural Language Processing (NLP). This paper aims to present an immersive introduction to LLMs from the perspective of generative models. The main components of the training process of LLMs are explained, and an example of LLMs for AI-g...
Hangzhou, where I am now living and which is most well-known for the West Lake, has recently witnessed the highest temperature this summer, 43 degrees Celsius. I studied and worked in this city for 12 years during the 1980s and 1990s, but had no impression of ever experiencing such hot weather during that time. Clearly, climate change is making hea...
Multi-objective optimization has burgeoned as a potent methodology for informed decision-making in enhanced geothermal systems, aiming to concurrently maximize economic yield, ensure enduring geothermal energy provision, and curtail carbon emissions. However, addressing a multitude of design parameters inherent in computationally intensive physics-...
Scientific innovation is pivotal for humanity, and harnessing large language models (LLMs) to generate research ideas could transform discovery. However, existing LLMs often produce simplistic and repetitive suggestions due to their limited ability in acquiring external knowledge for innovation. To address this problem, we introduce an enhanced pla...
The goal of relationship classification (RC) is to predict the semantic relationship between two entities in a given sentence. With the advent of deep learning and pretrained language models, RC research has progressed by leaps and bounds. However, the current studies are focused mainly on predicting semantic relationships from a predefined set. Ho...
In robust optimization problems, the magnitude of perturbations is relatively small. Consequently, solutions within certain regions are less likely to represent the robust optima when perturbations are introduced. Hence, a more efficient search process would benefit from increased opportunities to explore promising regions where global optima or go...
Sparse large-scale evolutionary multiobjective optimization has garnered substantial interest over the past years due to its significant practical implications. These optimization problems are characterized by a predominance of zero-valued decision variables in the Pareto optimal solutions. Most existing algorithms focus on exploiting the sparsity...
In this paper, we propose a multi-stage evolutionary framework with adaptive selection (MSEFAS) for efficiently handling constrained multi-objective optimization problems (CMOPs). MSEFAS has two stages of optimization in its early phase of evolutionary search: one stage that encourages promising infeasible solutions to approach the feasible region...
Adversarial training (AT) has become an effective defense method against adversarial examples (AEs) and it is typically framed as a bi-level optimization problem. Among various AT methods, fast AT (FAT), which employs a single-step attack strategy to guide the training process, can achieve good robustness against adversarial attacks at a low cost....
Deploying models across diverse devices demands tradeoffs among multiple objectives due to different resource constraints. Arguably, due to the small model trap problem in multi-objective neural architecture search (MO-NAS) based on a supernet, existing approaches may fail to maintain large models. Moreover, multi-tasking neural architecture search...
Train timetable rescheduling (TTR) aims to promptly restore the original operation of trains after unexpected disturbances or disruptions. Currently, this work is still done manually by train dispatchers, which is challenging to maintain performance under various problem instances. To mitigate this issue , this study proposes a reinforcement learni...
Multi-Task Evolutionary Optimization (MTEO), an important field focusing on addressing complex problems through optimizing multiple tasks simultaneously, has attracted much attention. While MTEO has been primarily focusing on task similarity, there remains a hugely untapped potential in harnessing the shared characteristics between different domain...
Federated learning (FL) has emerged as a promising paradigm for training models on decentralized data while safeguarding data privacy. Most existing FL systems, however, assume that all machine learning models are of the same type, although it becomes more likely that different edge devices adopt different types of AI models, including both convent...
Federated learning (FL) offers a privacy-preserving approach to machine learning for multiple collaborators without sharing raw data. However, the existence of non-independent and non-identically distributed (non-IID) datasets across different clients presents a significant challenge to FL, leading to a sharp drop in accuracy, reduced efficiency, a...
Federated multi-view clustering offers the potential to develop a global clustering model using data distributed across multiple devices. However, current methods face challenges due to the absence of label information and the paramount importance of data privacy. A significant issue is the feature heterogeneity across multi-view data, which compli...
Zero-Shot Learning (ZSL) aims to enable classifiers to identify unseen classes by enhancing data efficiency at the class level. This is achieved by generating image features from pre-defined semantics of unseen classes. However, most current approaches heavily depend on the number of samples from seen classes, i.e. they do not consider instance-lev...
Federated learning (FL) represents a pivotal shift in machine learning (ML) as it enables collaborative training of local ML models coordinated by a central aggregator, all without the need to exchange local data. However, its application on edge devices is hindered by limited computational capabilities and data communication challenges, compounded...
The perception layer of Internet of Things (IoT) not only needs to perceive service requests rapidly, but also considers reducing energy consumption intelligently. This issue becomes crucial in the scenario of large-scale IoT services. The existing research usually focus on one single aspect only, either energy consumption or perception rate. Inspi...
When I give a talk about evolutionary machine learning, one question I often expect is why I use an evolutionary algorithm to optimize the hyperparameters and structure of a neural network, rather than using a reinforcement learning algorithm. A quick answer might be, well, I am an evolutionary computation guy. I know this is a sloppy answer. Often...
Pauline Haddow is a Professor in the Department of Computer Science at the Norwegian University of Science and Technology (NTNU), Trondheim, Norway. She received a first-class honours degree from the University of Glasgow, Scotland in 1991 and her PhD in 1998 from NTNU, Norway. She has chaired the complex, reliable and adaptive systems lab (CRAB la...
With the scaling up of crude oil scheduling in modern refineries, large-scale crude oil scheduling problems (LSCOSPs) emerge with thousands of binary variables and non-linear constraints, which are challenging to be optimized by traditional optimization methods. To solve LSCOSPs, we take the practical crude oil scheduling from a marine-access refin...
In this paper, we propose a multi-objective optimization algorithm based on multitask conditional neural processes (MTCNPs) to deal with expensive multi-objective optimization problems (MOPs). In the proposed algorithm, an MOP is decomposed into several subproblems. Several related subproblems are assigned to a task group and jointly handled using...
Solving constrained multi-objective optimization problems with evolutionary algorithms has attracted considerable attention. Various constrained multi-objective optimization evolutionary algorithms (CMOEAs) have been developed with the use of different algorithmic strategies, evolutionary operators, and constraint-handling techniques. The performan...
Graph neural networks have received increased attention over the past years due to their promising ability to handle graph-structured data, which can be found in many real-world problems such as recommender systems and drug synthesis. Most existing research focuses on using graph neural networks to solve homophilous problems, and not much attention...
The digitization of process manufacturing involves converting information and knowledge into a digital format through technologies, such as artificial intelligence (AI), the Internet of Things (IoT), blockchain, and digital twins. This transformation promotes extension and optimization within the industrial, supply, and value chains, aiming to enha...
Dynamic multiobjective optimization problems (DMOPs) are characterized by multiple objectives that change over time in varying environments. More specifically, environmental changes can be described as various dynamics. However, it is difficult for existing dynamic multiobjective algorithms (DMOAs) to handle DMOPs due to their inability to learn in...
I am deeply honored to serve as the President of the IEEE Computational Intelligence Society (CIS) for 2024-2025. I had never imagined that I would become the President of our society when I joined IEEE at the 1998 World Congress on Computational Intelligence. I would take this opportunity to thank Bernadette Bouchon-Meunier, chair of the nominatio...
In recent years, a large number of approaches to constrained multi-objective optimization problems (CMOPs) have been proposed, focusing on developing tweaked strategies and techniques for handling constraints. However, an overly fine-tuned strategy or technique might overfit some problem types, resulting in a lack of versatility. In this article, w...
Efficient truck dispatching is crucial for optimizing container terminal operations within dynamic and complex scenarios. Despite good progress being made recently with more advanced uncertainty-handling techniques, existing approaches still have generalization issues and require considerable expertise and manual interventions in algorithm design....
Evolutionary algorithms (EAs) have significantly contributed to addressing large-scale crude oil scheduling problems (COSPs) that exceed the capabilities of mathematical programming. However, current research using EAs to resolve COSPs is limited to discrete-time models that assume uniform operation durations. While this simplification transforms C...
Structural balance in signed networks aims to search for the structure with the least imbalance of relationships. However, most existing studies focus on global structural balance, and little work has considered local structural balance. In this study, an optimization model is proposed based on the weak definition of structural balance theory. The...
Blackbox optimization problems are commonly seen in the real world, ranging from experimental design to hyperparameter tuning of machine learning models. In numerous scenarios, addressing a collection of similar data-driven blackbox optimization tasks distributed on multiple clients not only raises privacy concerns, but also suffers from non-indepe...
The Kriging model has been widely used in regression-based surrogate-assisted evolutionary algorithms (SAEAs) for expensive multiobjective optimization by using one model to approximate one objective, and the fusion of all the models forms the fitness surrogate. However, when tackling expensive many-objective optimization problems, too many models...
The implementation of distributed optimization, depending on the application, imposes escalating demands on communication and computational synchronization, with the general desire for the robust performance in the face of computationally slow agents and the avoidance of unnecessary communication. This paper proposes a distributed algorithm with as...
Deep learning has become increasingly important in fault diagnosis, but it relies on a large amount of high-quality labeled data. Collecting data from distributed machines can expand the dataset, but it usually leads to privacy concerns. Moreover, since the operating conditions are complex in real-world applications, the collected training data and...
When solving constrained optimization problems in real industrial processes, both optimality and computational efficiency need to be considered. However, most existing meta-heuristic algorithms are slow to find the global optimum. The first reason is that the way to generate and select candidate solutions is time-consuming. The low probability to g...
The massive increase of spam is posing a very serious threat to email and SMS, which have become an important means of communication. Not only do spams annoy users, but they also become a security threat. Machine learning techniques have been widely used for spam detection. Email spams can be detected through detecting senders' behaviour, the conte...
It is our great privilege to welcome you all to The 2015 Conference on Technologies and Applications of Artificial Intelligence (TAAI 2015) held from November 20 to November 22 in Tainan, Taiwan. The TAAI conference is an annual event that brings together researchers, engineers, and practitioners to present and exchange ideas, results, and experien...
Summary of synaptic plasticity data generated with τbAP,s = 55 ms and τNMDA,s = 152 ms. (a) Overall synaptic weight change generated by 100 spike pairings delivered at 5 Hz with βP = 0.45, βD = 0.24, kP = 0.04 and kD = 4 × 10-4, where kinase and phosphatase dynamics are controlled by peaks in intracellular calcium concentration. Horizontal dashed l...