Yuhui Shi

Liang Qu, Ningzhi Tang, Ruiqi Zheng et al.

Collaborative filtering (CF) based recommender systems are typically trained based on personal interaction data (e.g., clicks and purchases) that could be naturally represented as ego graphs. However, most existing recommendation methods collect these ego graphs from all users to compose a global graph to obtain high-order collaborative information between users and items, and these centralized CF recommendation methods inevitably lead to a high risk of user privacy leakage. Although recently proposed federated recommendation systems can mitigate the privacy problem, they either restrict the on-device local training to an isolated ego graph or rely on an additional third-party server to access other ego graphs resulting in a cumbersome pipeline, which is hard to work in practice. In addition, existing federated recommendation systems require resource-limited devices to maintain the entire embedding tables resulting in high communication costs. In light of this, we propose a semi-decentralized federated ego graph learning framework for on-device recommendations, named SemiDFEGL, which introduces new device-to-device collaborations to improve scalability and reduce communication costs and innovatively utilizes predicted interacted item nodes to connect isolated ego graphs to augment local subgraphs such that the high-order user-item collaborative information could be used in a privacy-preserving manner. Furthermore, the proposed framework is model-agnostic, meaning that it could be seamlessly integrated with existing graph neural network-based recommendation methods and privacy protection techniques. To validate the effectiveness of the proposed SemiDFEGL, extensive experiments are conducted on three public datasets, and the results demonstrate the superiority of the proposed SemiDFEGL compared to other federated recommendation methods.

Qi Zhao, Qiqi Duan, Bai Yan et al.

Metaheuristics have gained great success in academia and practice because their search logic can be applied to any problem with available solution representation, solution quality evaluation, and certain notions of locality. Manually designing metaheuristic algorithms for solving a target problem is criticized for being laborious, error-prone, and requiring intensive specialized knowledge. This gives rise to increasing interest in automated design of metaheuristic algorithms. With computing power to fully explore potential design choices, the automated design could reach and even surpass human-level design and could make high-performance algorithms accessible to a much wider range of researchers and practitioners. This paper presents a broad picture of automated design of metaheuristic algorithms, by conducting a survey on the common grounds and representative techniques in terms of design space, design strategies, performance evaluation strategies, and target problems in this field.

Beizhe Hu, Qiang Sheng, Juan Cao et al.

Detecting fake news requires both a delicate sense of diverse clues and a profound understanding of the real-world background, which remains challenging for detectors based on small language models (SLMs) due to their knowledge and capability limitations. Recent advances in large language models (LLMs) have shown remarkable performance in various tasks, but whether and how LLMs could help with fake news detection remains underexplored. In this paper, we investigate the potential of LLMs in fake news detection. First, we conduct an empirical study and find that a sophisticated LLM such as GPT 3.5 could generally expose fake news and provide desirable multi-perspective rationales but still underperforms the basic SLM, fine-tuned BERT. Our subsequent analysis attributes such a gap to the LLM's inability to select and integrate rationales properly to conclude. Based on these findings, we propose that current LLMs may not substitute fine-tuned SLMs in fake news detection but can be a good advisor for SLMs by providing multi-perspective instructive rationales. To instantiate this proposal, we design an adaptive rationale guidance network for fake news detection (ARG), in which SLMs selectively acquire insights on news analysis from the LLMs' rationales. We further derive a rationale-free version of ARG by distillation, namely ARG-D, which services cost-sensitive scenarios without querying LLMs. Experiments on two real-world datasets demonstrate that ARG and ARG-D outperform three types of baseline methods, including SLM-based, LLM-based, and combinations of small and large language models.

Qiong Nan, Danding Wang, Yongchun Zhu et al.

Both real and fake news in various domains, such as politics, health, and entertainment are spread via online social media every day, necessitating fake news detection for multiple domains. Among them, fake news in specific domains like politics and health has more serious potential negative impacts on the real world (e.g., the infodemic led by COVID-19 misinformation). Previous studies focus on multi-domain fake news detection, by equally mining and modeling the correlation between domains. However, these multi-domain methods suffer from a seesaw problem: the performance of some domains is often improved at the cost of hurting the performance of other domains, which could lead to an unsatisfying performance in specific domains. To address this issue, we propose a Domain- and Instance-level Transfer Framework for Fake News Detection (DITFEND), which could improve the performance of specific target domains. To transfer coarse-grained domain-level knowledge, we train a general model with data of all domains from the meta-learning perspective. To transfer fine-grained instance-level knowledge and adapt the general model to a target domain, we train a language model on the target domain to evaluate the transferability of each data instance in source domains and re-weigh each instance's contribution. Offline experiments on two datasets demonstrate the effectiveness of DITFEND. Online experiments show that DITFEND brings additional improvements over the base models in a real-world scenario.

Lijun Sun, Yu-Cheng Chang, Chao Lyu et al.

The multiple-target self-organizing pursuit (SOP) problem has wide applications and has been considered a challenging self-organization game for distributed systems, in which intelligent agents cooperatively pursue multiple dynamic targets with partial observations. This work proposes a framework for decentralized multi-agent systems to improve the implicit coordination capabilities in search and pursuit. We model a self-organizing system as a partially observable Markov game (POMG) featured by large-scale, decentralization, partial observation, and noncommunication. The proposed distributed algorithm: fuzzy self-organizing cooperative coevolution (FSC2) is then leveraged to resolve the three challenges in multi-target SOP: distributed self-organizing search (SOS), distributed task allocation, and distributed single-target pursuit. FSC2 includes a coordinated multi-agent deep reinforcement learning (MARL) method that enables homogeneous agents to learn natural SOS patterns. Additionally, we propose a fuzzy-based distributed task allocation method, which locally decomposes multi-target SOP into several single-target pursuit problems. The cooperative coevolution principle is employed to coordinate distributed pursuers for each single-target pursuit problem. Therefore, the uncertainties of inherent partial observation and distributed decision-making in the POMG can be alleviated. The experimental results demonstrate that by decomposing the SOP task, FSC2 achieves superior performance compared with other implicit coordination policies fully trained by general MARL algorithms. The scalability of FSC2 is proved that up to 2048 FSC2 agents perform efficient multi-target SOP with almost 100 percent capture rates. Empirical analyses and ablation studies verify the interpretability, rationality, and effectiveness of component algorithms in FSC2.

Yijun Yang, Tianyi Zhou, Kanxue Li et al.

While large language models (LLMs) excel in a simulated world of texts, they struggle to interact with the more realistic world without perceptions of other modalities such as visual or audio signals. Although vision-language models (VLMs) integrate LLM modules (1) aligned with static image features, and (2) may possess prior knowledge of world dynamics (as demonstrated in the text world), they have not been trained in an embodied visual world and thus cannot align with its dynamics. On the other hand, training an embodied agent in a noisy visual world without expert guidance is often challenging and inefficient. In this paper, we train a VLM agent living in a visual world using an LLM agent excelling in a parallel text world. Specifically, we distill LLM's reflection outcomes (improved actions by analyzing mistakes) in a text world's tasks to finetune the VLM on the same tasks of the visual world, resulting in an Embodied Multi-Modal Agent (EMMA) quickly adapting to the visual world dynamics. Such cross-modality imitation learning between the two parallel worlds is achieved by a novel DAgger-DPO algorithm, enabling EMMA to generalize to a broad scope of new tasks without any further guidance from the LLM expert. Extensive evaluations on the ALFWorld benchmark's diverse tasks highlight EMMA's superior performance to SOTA VLM-based agents, e.g., 20%-70% improvement in the success rate.

Zeneng She, Wenjian Luo, Xin Lin et al.

In the field of evolutionary multiobjective optimization, the decision maker (DM) concerns conflicting objectives. In the real-world applications, there usually exist more than one DM and each DM concerns parts of these objectives. Multiparty multiobjective optimization problems (MPMOPs) are proposed to depict the MOP with multiple decision makers involved, where each party concerns about certain some objectives of all. However, in the evolutionary computation field, there is not much attention paid on MPMOPs. This paper constructs a series of MPMOPs based on distance minimization problems (DMPs), whose Pareto optimal solutions can be vividly visualized. To address MPMOPs, the new proposed algorithm OptMPNDS3 uses the multiparty initializing method to initialize the population and takes JADE2 operator to generate the offsprings. OptMPNDS3 is compared with OptAll, OptMPNDS and OptMPNDS2 on the problem suite. The result shows that OptMPNDS3 is strongly comparable to other algorithms

Qi Zhou, Zipeng Ye, Yubo Tang et al.

Deep Neural Networks (DNNs) have been widely used in many areas such as autonomous driving and face recognition. However, DNN model is fragile to backdoor attack. A backdoor in the DNN model can be activated by a poisoned input with trigger and leads to wrong prediction, which causes serious security issues in applications. It is challenging for current defenses to eliminate the backdoor effectively with limited computing resources, especially when the sizes and numbers of the triggers are variable as in the physical world. We propose an efficient backdoor defense based on evolutionary trigger detection and lightweight model repair. In the first phase of our method, CAM-focus Evolutionary Trigger Filter (CETF) is proposed for trigger detection. CETF is an effective sample-preprocessing based method with the evolutionary algorithm, and our experimental results show that CETF not only distinguishes the images with triggers accurately from the clean images, but also can be widely used in practice for its simplicity and stability in different backdoor attack situations. In the second phase of our method, we leverage several lightweight unlearning methods with the trigger detected by CETF for model repair, which also constructively demonstrate the underlying correlation of the backdoor with Batch Normalization layers. Source code will be published after accepted.

Lijun Sun, Chao Lyu, Yuhui Shi

The pursuit domain, or predator-prey problem is a standard testbed for the study of coordination techniques. In spite that its problem setup is apparently simple, it is challenging for the research of the emerged swarm intelligence. This paper presents a particle swarm optimization (PSO) based cooperative coevolutionary algorithm for the (predator) robots, called CCPSO-R, where real and virtual robots coexist in an evolutionary algorithm (EA). Virtual robots sample and explore the vicinity of the corresponding real robots and act as their action spaces, while the real robots consist of the real predators who actually pursue the prey robot without fixed behavior rules under the immediate guidance of the fitness function, which is designed in a modular manner with very limited domain knowledge. In addition, kinematic limits and collision avoidance considerations are integrated into the update rules of robots. Experiments are conducted on a scalable swarm of predator robots with 4 types of preys, the results of which show the reliability, generality, and scalability of the proposed CCPSO-R. Comparison with a representative dynamic path planning based algorithm Multi-Agent Real-Time Pursuit (MAPS) further shows the effectiveness of CCPSO-R. Finally, the codes of this paper are public available at: https://github.com/LijunSun90/pursuitCCPSOR.

Lijun Sun, Yijun Yang, Qiqi Duan et al.

Multi-agent coordination studies the underlying mechanism enabling the trending spread of diverse multi-agent systems (MAS) and has received increasing attention, driven by the expansion of emerging applications and rapid AI advances. This survey outlines the current state of coordination research across applications through a unified understanding that answers four fundamental coordination questions: (1) what is coordination; (2) why coordination; (3) who to coordinate with; and (4) how to coordinate. Our purpose is to explore existing ideas and expertise in coordination and their connections across diverse applications, while identifying and highlighting emerging and promising research directions. First, general coordination problems that are essential to varied applications are identified and analyzed. Second, a number of MAS applications are surveyed, ranging from widely studied domains, e.g., search and rescue, warehouse automation and logistics, and transportation systems, to emerging fields including humanoid and anthropomorphic robots, satellite systems, and large language models (LLMs). Finally, open challenges about the scalability, heterogeneity, and learning mechanisms of MAS are analyzed and discussed. In particular, we identify the hybridization of hierarchical and decentralized coordination, human-MAS coordination, and LLM-based MAS as promising future directions.

Wenjian Luo, Peilan Xu, Shengxiang Yang et al.

The competition focuses on Multiparty Multiobjective Optimization Problems (MPMOPs), where multiple decision makers have conflicting objectives, as seen in applications like UAV path planning. Despite their importance, MPMOPs remain understudied in comparison to conventional multiobjective optimization. The competition aims to address this gap by encouraging researchers to explore tailored modeling approaches. The test suite comprises two parts: problems with common Pareto optimal solutions and Biparty Multiobjective UAV Path Planning (BPMO-UAVPP) problems with unknown solutions. Optimization algorithms for the first part are evaluated using Multiparty Inverted Generational Distance (MPIGD), and the second part is evaluated using Multiparty Hypervolume (MPHV) metrics. The average algorithm ranking across all problems serves as a performance benchmark.

Liang Qu, Cunze Wang, Yuhui Shi

The application of deep learning techniques to medical problems has garnered widespread research interest in recent years, such as applying convolutional neural networks to medical image classification tasks. However, data in the medical field is often highly private, preventing different hospitals from sharing data to train an accurate model. Federated learning, as a privacy-preserving machine learning architecture, has shown promising performance in balancing data privacy and model utility by keeping private data on the client's side and using a central server to coordinate a set of clients for model training through aggregating their uploaded model parameters. Yet, this architecture heavily relies on a trusted third-party server, which is challenging to achieve in real life. Swarm learning, as a specialized decentralized federated learning architecture that does not require a central server, utilizes blockchain technology to enable direct parameter exchanges between clients. However, the mining of blocks requires significant computational resources, limiting its scalability. To address this issue, this paper integrates the brain storm optimization algorithm into the swarm learning framework, named BSO-SL. This approach clusters similar clients into different groups based on their model distributions. Additionally, leveraging the architecture of BSO, clients are given the probability to engage in collaborative learning both within their cluster and with clients outside their cluster, preventing the model from converging to local optima. The proposed method has been validated on a real-world diabetic retinopathy image classification dataset, and the experimental results demonstrate the effectiveness of the proposed approach.

Yijun Yang, Tianyi Zhou, Jing Jiang et al.

How to train a generalizable meta-policy by continually learning a sequence of tasks? It is a natural human skill yet challenging to achieve by current reinforcement learning: the agent is expected to quickly adapt to new tasks (plasticity) meanwhile retaining the common knowledge from previous tasks (stability). We address it by "Continual Task Allocation via Sparse Prompting (CoTASP)", which learns over-complete dictionaries to produce sparse masks as prompts extracting a sub-network for each task from a meta-policy network. CoTASP trains a policy for each task by optimizing the prompts and the sub-network weights alternatively. The dictionary is then updated to align the optimized prompts with tasks' embedding, thereby capturing tasks' semantic correlations. Hence, relevant tasks share more neurons in the meta-policy network due to similar prompts while cross-task interference causing forgetting is effectively restrained. Given a meta-policy and dictionaries trained on previous tasks, new task adaptation reduces to highly efficient sparse prompting and sub-network finetuning. In experiments, CoTASP achieves a promising plasticity-stability trade-off without storing or replaying any past tasks' experiences. It outperforms existing continual and multi-task RL methods on all seen tasks, forgetting reduction, and generalization to unseen tasks.

Wenjian Luo, Xin Lin, Changhe Li et al.

Dynamic and multimodal features are two important properties and widely existed in many real-world optimization problems. The former illustrates that the objectives and/or constraints of the problems change over time, while the latter means there is more than one optimal solution (sometimes including the accepted local solutions) in each environment. The dynamic multimodal optimization problems (DMMOPs) have both of these characteristics, which have been studied in the field of evolutionary computation and swarm intelligence for years, and attract more and more attention. Solving such problems requires optimization algorithms to simultaneously track multiple optima in the changing environments. So that the decision makers can pick out one optimal solution in each environment according to their experiences and preferences, or quickly turn to other solutions when the current one cannot work well. This is very helpful for the decision makers, especially when facing changing environments. In this competition, a test suit about DMMOPs is given, which models the real-world applications. Specifically, this test suit adopts 8 multimodal functions and 8 change modes to construct 24 typical dynamic multimodal optimization problems. Meanwhile, the metric is also given to measure the algorithm performance, which considers the average number of optimal solutions found in all environments. This competition will be very helpful to promote the development of dynamic multimodal optimization algorithms.

Qi Zhao, Bai Yan, Yuhui Shi

In many clustering scenes, data samples' attribute values change over time. For such data, we are often interested in obtaining a partition for each time step and tracking the dynamic change of partitions. Normally, a smooth change is assumed for data to have a temporal smooth nature. Existing algorithms consider the temporal smoothness as an a priori preference and bias the search towards the preferred direction. This a priori manner leads to a risk of converging to an unexpected region because it is not always the case that a reasonable preference can be elicited given the little prior knowledge about the data. To address this issue, this paper proposes a new clustering framework called evolutionary robust clustering over time. One significant innovation of the proposed framework is processing the temporal smoothness in an a posteriori manner, which avoids unexpected convergence that occurs in existing algorithms. Furthermore, the proposed framework automatically tunes the weight of smoothness without data's affinity matrix and predefined parameters, which holds better applicability and scalability. The effectiveness and efficiency of the proposed framework are confirmed by comparing with state-of-the-art algorithms on both synthetic and real datasets.

Liang Qu, Huaisheng Zhu, Ruiqi Zheng et al.

Imbalanced classification on graphs is ubiquitous yet challenging in many real-world applications, such as fraudulent node detection. Recently, graph neural networks (GNNs) have shown promising performance on many network analysis tasks. However, most existing GNNs have almost exclusively focused on the balanced networks, and would get unappealing performance on the imbalanced networks. To bridge this gap, in this paper, we present a generative adversarial graph network model, called ImGAGN to address the imbalanced classification problem on graphs. It introduces a novel generator for graph structure data, named GraphGenerator, which can simulate both the minority class nodes' attribute distribution and network topological structure distribution by generating a set of synthetic minority nodes such that the number of nodes in different classes can be balanced. Then a graph convolutional network (GCN) discriminator is trained to discriminate between real nodes and fake (i.e., generated) nodes, and also between minority nodes and majority nodes on the synthetic balanced network. To validate the effectiveness of the proposed method, extensive experiments are conducted on four real-world imbalanced network datasets. Experimental results demonstrate that the proposed method ImGAGN outperforms state-of-the-art algorithms for semi-supervised imbalanced node classification task.

Jian Yang, Yuhui Shi

Coordinated motion control in swarm robotics aims to ensure the coherence of members in space, i.e., the robots in a swarm perform coordinated movements to maintain spatial structures. This problem can be modeled as a tracking control problem, in which individuals in the swarm follow a target position with the consideration of specific relative distance or orientations. To keep the communication cost low, the PID controller can be utilized to achieve the leader-follower tracking control task without the information of leader velocities. However, the controller's parameters need to be optimized to adapt to situations changing, such as the different swarm population, the changing of the target to be followed, and the anti-collision demands, etc. In this letter, we apply a modified Brain Storm Optimization (BSO) algorithm to an incremental PID tracking controller to get the relatively optimal parameters adaptively for leader-follower formation control for swarm robotics. Simulation results show that the proposed method could reach the optimal parameters during robot movements. The flexibility and scalability are also validated, which ensures that the proposed method can adapt to different situations and be a good candidate for coordinated motion control for swarm robotics in more realistic scenarios.

Jian Yang, Yuhui Shi

Swarm intelligence optimization algorithms can be adopted in swarm robotics for target searching tasks in a 2-D or 3-D space by treating the target signal strength as fitness values. Many current works in the literature have achieved good performance in single-target search problems. However, when there are multiple targets in an environment to be searched, many swarm intelligence-based methods may converge to specific locations prematurely, making it impossible to explore the environment further. The Brain Storm Optimization (BSO) algorithm imitates a group of humans in solving problems collectively. A series of guided searches can finally obtain a relatively optimal solution for particular optimization problems. Furthermore, with a suitable clustering operation, it has better multi-modal optimization performance, i.e., it can find multiple optima in the objective space. By matching the members in a robotic swarm to the individuals in the algorithm under both environments and robots constraints, this paper proposes a BSO-based collaborative searching framework for swarm robotics called Robotic BSO. The simulation results show that the proposed method can simulate the BSO's guided search characteristics and has an excellent prospect for multi-target searching problems for swarm robotics.

Jian Yang, Yuhui Shi

Population-based methods are often used to solve multimodal optimization problems. By combining niching or clustering strategy, the state-of-the-art approaches generally divide the population into several subpopulations to find multiple solutions for a problem at hand. However, these methods only guided by the fitness value during iterations, which are suffering from determining the number of subpopulations, i.e., the number of niche areas or clusters. To compensate for this drawback, this paper presents an Attention-oriented Brain Storm Optimization (ABSO) method that introduces the attention mechanism into a relatively new swarm intelligence algorithm, i.e., Brain Storm Optimization (BSO). By converting the objective space from the fitness space into "attention" space, the individuals are clustered and updated iteratively according to their salient values. Rather than converge to a single global optimum, the proposed method can guide the search procedure to converge to multiple "salient" solutions. The preliminary results show that the proposed method can locate multiple global and local optimal solutions of several multimodal benchmark functions. The proposed method needs less prior knowledge of the problem and can automatically converge to multiple optimums guided by the attention mechanism, which has excellent potential for further development.

Yurui Ming, Dongrui Wu, Yu-Kai Wang et al.

Fatigue is the most vital factor of road fatalities and one manifestation of fatigue during driving is drowsiness. In this paper, we propose using deep Q-learning to analyze an electroencephalogram (EEG) dataset captured during a simulated endurance driving test. By measuring the correlation between drowsiness and driving performance, this experiment represents an important brain-computer interface (BCI) paradigm especially from an application perspective. We adapt the terminologies in the driving test to fit the reinforcement learning framework, thus formulate the drowsiness estimation problem as an optimization of a Q-learning task. By referring to the latest deep Q-Learning technologies and attending to the characteristics of EEG data, we tailor a deep Q-network for action proposition that can indirectly estimate drowsiness. Our results show that the trained model can trace the variations of mind state in a satisfactory way against the testing EEG data, which demonstrates the feasibility and practicability of this new computation paradigm. We also show that our method outperforms the supervised learning counterpart and is superior for real applications. To the best of our knowledge, we are the first to introduce the deep reinforcement learning method to this BCI scenario, and our method can be potentially generalized to other BCI cases.

Bin Liu, Shi Cheng, Yuhui Shi

In this paper, we are concerned with a branch of evolutionary algorithms termed estimation of distribution (EDA), which has been successfully used to tackle derivative-free global optimization problems. For existent EDA algorithms, it is a common practice to use a Gaussian distribution or a mixture of Gaussian components to represent the statistical property of available promising solutions found so far. Observing that the Student's t distribution has heavier and longer tails than the Gaussian, which may be beneficial for exploring the solution space, we propose a novel EDA algorithm termed ESTDA, in which the Student's t distribution, rather than Gaussian, is employed. To address hard multimodal and deceptive problems, we extend ESTDA further by substituting a single Student's t distribution with a mixture of Student's t distributions. The resulting algorithm is named as estimation of mixture of Student's t distribution algorithm (EMSTDA). Both ESTDA and EMSTDA are evaluated through extensive and in-depth numerical experiments using over a dozen of benchmark objective functions. Empirical results demonstrate that the proposed algorithms provide remarkably better performance than their Gaussian counterparts.

Jun Sun, Xiaojun Wu, Vasile Palade et al.

The random drift particle swarm optimization (RDPSO) algorithm, inspired by the free electron model in metal conductors placed in an external electric field, is presented, systematically analyzed and empirically studied in this paper. The free electron model considers that electrons have both a thermal and a drift motion in a conductor that is placed in an external electric field. The motivation of the RDPSO algorithm is described first, and the velocity equation of the particle is designed by simulating the thermal motion as well as the drift motion of the electrons, both of which lead the electrons to a location with minimum potential energy in the external electric field. Then, a comprehensive analysis of the algorithm is made, in order to provide a deep insight into how the RDPSO algorithm works. It involves a theoretical analysis and the simulation of the stochastic dynamical behavior of a single particle in the RDPSO algorithm. The search behavior of the algorithm itself is also investigated in detail, by analyzing the interaction between the particles. Some variants of the RDPSO algorithm are proposed by incorporating different random velocity components with different neighborhood topologies. Finally, empirical studies on the RDPSO algorithm are performed by using a set of benchmark functions from the CEC2005 benchmark suite. Based on the theoretical analysis of the particle's behavior, two methods of controlling the algorithmic parameters are employed, followed by an experimental analysis on how to select the parameter values, in order to obtain a good overall performance of the RDPSO algorithm and its variants in real-world applications. A further performance comparison between the RDPSO algorithms and other variants of PSO is made to prove the efficiency of the RDPSO algorithms.