Chao Yan

IROS Conference 2025 Conference Paper

Emergent Cooperative Strategies for Pursuit-Evasion in Cluttered Environments: A Knowledge-Enhanced Multi-Agent Deep Reinforcement Learning Approach

• Yihao Sun
• Chao Yan
• Han Zhou
• Xiaojia Xiang
• Jie Jiang

Deep reinforcement learning (DRL) has recently emerged as a promising tool for tackling pursuit-evasion tasks. However, most existing DRL-based pursuit approaches still rely on individual rewards and struggle with complex scenarios. To address these challenges, we propose a knowledge-enhanced DRL approach for multi-agent pursuit-evasion in complex environments. Specifically, the cooperative pursuit problem is modeled as a decentralized partially observable Markov decision process from each pursuers perspective, where the team reward function is elaborately designed to encourage collaborative behavior and enhance team coordination. Then, a novel knowledge enhanced multi-agent twin delayed deep deterministic policy gradient (KE-MATD3) algorithm is presented to efficiently learn the cooperative pursuit policy. By integrating a knowledge enhancement mechanism that extracts effective information from an improved artificial potential field method, the cooperative pursuit policy achieves more robust convergence, mitigating the local optima that typically arise from individual reward-based learning. Finally, extensive numerical simulations and real-world experiments validate the efficiency and superiority of the proposed approach, demonstrating emergent cooperative behaviors among the pursuers.

JBHI Journal 2025 Journal Article

MTSNet: Convolution-Based Transformer Network With Multi-Scale Temporal-Spectral Feature Fusion for SSVEP Signal Decoding

• Zhen Lan
• Zixing Li
• Chao Yan
• Xiaojia Xiang
• Dengqing Tang
• Min Wu
• Zhenghua Chen

Improving the decoding performance of steady-state visual evoked (SSVEP) signals is crucial for the practical application of SSVEP-based brain-computer interface (BCI) systems. Although numerous methods have achieved impressive results in decoding SSVEP signals, most of them focus only on the temporal or spectral domain information or concatenate them directly, which may ignore the complementary relationship between different features. To address this issue, we propose a dual-branch convolution-based Transformer network with multi-scale temporal-spectral feature fusion, termed MTSNet, to improve the decoding performance of SSVEP signals. Specifically, the temporal branch extracts temporal features from the SSVEP signals using the multi-level convolution- based Transformer (Convformer) that can adapt to the dynamic fluctuations of SSVEP signals. In parallel, the spectral branch takes the complex spectrum converted from temporal signals by the zero-padding fast Fourier transform as input and uses the Convformer to extract spectral features. These extracted temporal and spectral features are then integrated by the multi-scale feature fusion module to obtain comprehensive features with different scale information, thereby enhancing the interactions between the features and improving the effectiveness and robustness. Extensive experimental results on two widely used public SSVEP datasets, Benchmark and BETA, show that the proposed MTSNet significantly outperforms the state-of-the-art calibration-free methods in terms of accuracy and ITR. The superior performance demonstrates the effectiveness of our method in decoding SSVEP signals, which may facilitate the practical application of SSVEP-based BCI systems.

YNIMG Journal 2025 Journal Article

Neural correlates of olfactory working memory in the human brain

• Zhuofeng Li
• Shu-bin Li
• Shaozhen Tan
• Lu-lu Liu
• Chao Yan
• Lai-quan Zou

Previous research has revealed that the insula, pallidum, thalamus, hippocampus, middle frontal gyrus, and supplementary motor area are activated during odor memory and that the performance of olfactory working memory is affected by the verbalization of odors. However, the neural mechanisms underlying olfactory working memory and the role of verbalization in olfactory working memory are not fully understood. Twenty-nine participants were enrolled in a study to complete olfactory and visual n-back tasks using high- and low-verbalizability stimuli while undergoing fMRI imaging. The behavioral results showed that the participants achieved greater accuracy in the visual rather than olfactory n-back task. We observed increased activation in the precentral gyrus, superior frontal gyrus, middle frontal gyrus, supplementary motor area, and inferior parietal gyrus during olfactory working memory. Interestingly, decreased activation was observed in the olfactory 2-back task versus the 0-back task. Moreover, the left angular gyrus and inferior parietal gyrus were more strongly activated during processing of olfactory working memory using high-verbalizability odors. In conclusion, olfactory working memory engages cross-modal regions to facilitate responses, is involved in the monitoring and manipulation of information during working memory, and boasts a unique activation pattern that is different from that of visual working memory. Semantic information supports the representation of odor information in the working memory system.

TIST Journal 2024 Journal Article

Popularity Bias in Correlation Graph-based API Recommendation for Mashup Creation

• Chao Yan
• Weiyi Zhong
• Dengshuai Zhai
• Arif Ali Khan
• Wenwen Gong
• Yanwei Xu
• Baogui Xin

The explosive growth of the Application Programming Interfaces (APIs) economy in recent years has led to a dramatic increase in available APIs. Mashup development, a dominant approach for creating data-centric applications based on APIs, has experienced a surge in popularity. However, the vast array of choices poses a challenge for mashup developers when selecting appropriate API compositions to meet specific business requirements. Correlation graph-based recommendation approaches have been designed to assist developers in discovering related and compatible API compositions for mashup creation. Unfortunately, these approaches often suffer from popularity bias issues, leading to an inequality in API usage and potential disruptions to the entire API ecosystem. To address these challenges, our research begins with a theoretical analysis of the popularity bias introduced by correlation graph-based API recommendation approaches. Subsequently, we empirically validate the presence of popularity bias in API recommendations through a data-driven study. Finally, we introduce the p opularity b ias aware w eb A PI r ecommendation ( PB-WAR ) approach to mitigate popularity bias in correlation graph-based API recommendations. Experimental results over a real-world dataset demonstrate that PB-WAR offers the optimal tradeoff between accuracy and debiasing performance compared to other competitive methods.

NeurIPS Conference 2023 Conference Paper

A Comprehensive Study on Text-attributed Graphs: Benchmarking and Rethinking

• Hao Yan
• Chaozhuo Li
• Ruosong Long
• Chao Yan
• Jianan Zhao
• Wenwen Zhuang
• Jun Yin
• Peiyan Zhang

Text-attributed graphs (TAGs) are prevalent in various real-world scenarios, where each node is associated with a text description. The cornerstone of representation learning on TAGs lies in the seamless integration of textual semantics within individual nodes and the topological connections across nodes. Recent advancements in pre-trained language models (PLMs) and graph neural networks (GNNs) have facilitated effective learning on TAGs, garnering increased research interest. However, the absence of meaningful benchmark datasets and standardized evaluation procedures for TAGs has impeded progress in this field. In this paper, we propose CS-TAG, a comprehensive and diverse collection of challenging benchmark datasets for TAGs. The CS-TAG datasets are notably large in scale and encompass a wide range of domains, spanning from citation networks to purchase graphs. In addition to building the datasets, we conduct extensive benchmark experiments over CS-TAG with various learning paradigms, including PLMs, GNNs, PLM-GNN co-training methods, and the proposed novel topological pre-training of language models. In a nutshell, we provide an overview of the CS-TAG datasets, standardized evaluation procedures, and present baseline experiments. The entire CS-TAG project is publicly accessible at \url{https: //github. com/sktsherlock/TAG-Benchmark}.

NeurIPS Conference 2023 Conference Paper

Private Everlasting Prediction

• Moni Naor
• Kobbi Nissim
• Uri Stemmer
• Chao Yan

A private learner is trained on a sample of labeled points and generates a hypothesis that can be used for predicting the labels of newly sampled points while protecting the privacy of the training set [Kasiviswannathan et al. , FOCS 2008]. Past research uncovered that private learners may need to exhibit significantly higher sample complexity than non-private learners as is the case of learning of one-dimensional threshold functions [Bun et al. , FOCS 2015, Alon et al. , STOC 2019]. We explore prediction as an alternative to learning. A predictor answers a stream of classification queries instead of outputting a hypothesis. Earlier work has considered a private prediction model with a single classification query [Dwork and Feldman, COLT 2018]. We observe that when answering a stream of queries, a predictor must modify the hypothesis it uses over time, and in a manner that cannot rely solely on the training set. We introduce {\em private everlasting prediction} taking into account the privacy of both the training set {\em and} the (adaptively chosen) queries made to the predictor. We then present a generic construction of private everlasting predictors in the PAC model. The sample complexity of the initial training sample in our construction is quadratic (up to polylog factors) in the VC dimension of the concept class. Our construction allows prediction for all concept classes with finite VC dimension, and in particular threshold functions over infinite domains, for which (traditional) private learning is known to be impossible.

IROS Conference 2022 Conference Paper

Attention-Based Population-Invariant Deep Reinforcement Learning for Collision-Free Flocking with A Scalable Fixed-Wing UAV Swarm

• Chao Yan
• Kin Huat Low
• Xiaojia Xiang
• Tianjiang Hu
• Lincheng Shen

A swarm of fixed-wing unmanned aerial vehicles (UAVs) is expected to efficiently accomplish various tasks in complex scenarios. This paper proposes an attention-based population-invariant multi-agent deep reinforcement learning (MADRL) approach to deal with the decentralized collision-free flocking problem for a scalable fixed-wing UAV swarm. First, this problem is modeled as a decentralized partially observable Markov decision process from the perspective of each follower. Then, an improved multi-agent deep deterministic policy gradient (MADDPG) algorithm is presented to efficiently learn the population-invariant flocking policy. In this algorithm, the parameter sharing with ego-centric representation mechanism is incorporated to improve learning efficiency. Besides, the attention-based population-invariant network structure (APINet) is designed by leveraging the self-attention mechanism. With this structure, the learned flocking policy is invariant to the population of the swarm. Finally, both numerical and hardware-in-the-loop simulation results verify the efficiency and scalability of the proposed approach.

IROS Conference 2021 Conference Paper

Flocking and Collision Avoidance for a Dynamic Squad of Fixed-Wing UAVs Using Deep Reinforcement Learning

• Chao Yan
• Xiaojia Xiang
• Chang Wang 0005
• Zhen Lan

Developing the flocking behavior for a dynamic squad of fixed-wing UAVs is still a challenge due to kinematic complexity and environmental uncertainty. In this paper, we deal with the decentralized flocking and collision avoidance problem through deep reinforcement learning (DRL). Specifically, we formulate a decentralized DRL-based decision making framework from the perspective of every follower, where a collision avoidance mechanism is integrated into the flocking controller. Then, we propose a novel reinforcement learning algorithm PS-CACER for training a shared control policy for all the followers. Besides, we design a plug-n-play embedding module based on convolutional neural networks and the attention mechanism. As a result, the variable-length system state can be encoded into a fixed-length embedding vector, which makes the learned DRL policy independent with the number and the order of followers. Finally, numerical simulation results demonstrate the effectiveness of the proposed method, and the learned policies can be directly transferred to semi-physical simulation without any parameter finetuning.

AAAI Conference 2020 Conference Paper

Finding Needles in a Moving Haystack: Prioritizing Alerts with Adversarial Reinforcement Learning

• Liang Tong
• Aron Laszka
• Chao Yan
• Ning Zhang
• Yevgeniy Vorobeychik

Detection of malicious behavior is a fundamental problem in security. One of the major challenges in using detection systems in practice is in dealing with an overwhelming number of alerts that are triggered by normal behavior (the so-called false positives), obscuring alerts resulting from actual malicious activities. We introduce a novel approach for computing a policy for prioritizing alerts using adversarial reinforcement learning. Our approach assumes that the attacker knows the full state of the detection system and the defender’s alert prioritization policy, and will dynamically choose an optimal attack. The first step of our approach is to capture the interaction between the defender and attacker in a game theoretic model. To tackle the computational complexity of solving this game to obtain a dynamic stochastic alert prioritization policy, we propose an adversarial reinforcement learning framework. In this framework, we use neural reinforcement learning to compute best response policies for both the defender and the adversary to an arbitrary stochastic policy of the other. We then use these in a double-oracle framework to obtain an approximate equilibrium of the game, which in turn yields a robust stochastic policy for the defender. We use case studies in network intrusion and fraud detection to demonstrate that our approach is effective in creating robust alert prioritization policies. 1

AAAI Conference 2016 Conference Paper

Learning to Appreciate the Aesthetic Effects of Clothing

• Jia Jia
• Jie Huang
• Guangyao Shen
• Tao He
• Zhiyuan Liu
• Huanbo Luan
• Chao Yan

How do people describe clothing? The words like “formal” or “casual” are usually used. However, recent works often focus on recognizing or extracting visual features (e. g. , sleeve length, color distribution and clothing pattern) from clothing images accurately. How can we bridge the gap between the visual features and the aesthetic words? In this paper, we formulate this task to a novel three-level framework: visual features (VF) image-scale space (ISS) - aesthetic words space (AWS). Leveraging the art-field image-scale space served as an intermediate layer, we first propose a Stacked Denoising Autoencoder Guided by Correlative Labels (SDAE- GCL) to map the visual features to the image-scale space; and then according to the semantic distances computed by WordNet: :Similarity, we map the most often used aesthetic words in online clothing shops to the image-scale space too. Employing upper-body menswear images downloaded from several global online clothing shops as experimental data, the results indicate that the proposed three-level framework can help to capture the subtle relationship between visual features and aesthetic words better compared to several baselines. To demonstrate that our three-level framework and its implementation methods are universally applicable, we finally present some interesting analyses on the fashion trend of menswear in the last 10 years.

EAAI Journal 1990 Journal Article

Innovative applications of artificial intelligence

• Chao Yan