Author name cluster

Jixiang Li

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

6 papers

1 author row

EAAI Journal 2026 Journal Article

Multi-agent deep reinforcement learning for group intelligence in emergency evacuation: A decentralized simulation-to-reality platform with perception-aware policies

Jixiang Li
Baishu Wan
Zhigong Song

Multi-agent deep reinforcement learning (MADRL) enables agents to learn and optimize their policies through interactions within a shared environment, addressing both cooperation and competition challenges. In this work, we develop a MADRL framework specifically engineered for dynamic and complex environments, aiming to bridge the gap between simulation and real-world deployment. The proposed framework adopts a multi-scenario and multi-stage policy gradient approach with a decentralized training and execution structure, allowing agents to seamlessly transfer their learned behaviors to real-world applications such as emergency evacuation. Simulation results further demonstrate that the framework identifies optimal evacuation routes, referred to as "escape arcs, " from collision heatmaps. These arcs represent paths that minimize congestion and maximize safe evacuation. In deployment, the generated policies have demonstrated versatility, effectively handling complex situations and showing significant potential for applications in public safety and emergency response.

Details DOI

JBHI Journal 2024 Journal Article

End-to-End Multimodal Emotion Recognition Based on Facial Expressions and Remote Photoplethysmography Signals

Jixiang Li
Jianxin Peng

Emotion is a complex physiological phenomenon, and a single modality may be insufficient for accurately determining human emotional states. This paper proposes an end-to-end multimodal emotion recognition method based on facial expressions and non-contact physiological signals. Facial expression features and remote photoplethysmography (rPPG) signals are extracted from facial video data, and a transformer-based cross-modal attention mechanism (TCMA) is used to learn the correlation between the two modalities. The results show that the accuracy of emotion recognition can be slightly improved by combining facial expressions with accurate rPPG signals. The performance is further improved with the use of TCMA, for which the binary classification accuracy of valence and arousal is 91. 11% and 90. 00%, respectively. Additionally, when experiments are conducted using the whole dataset, an increased accuracy of 7. 31% and 4. 23% for the binary classification of valence and arousal, and an improved accuracy of 5. 36% for the four classifications of valence-arousal are achieved when TCMA is used in modal fusion, compared to using only facial expression modality, which fully demonstrates the effectiveness and robustness of TCMA. This method makes it possible to realize multimodal emotion recognition of facial expressions and contactless physiological signals in reality.

Details DOI

JBHI Journal 2024 Journal Article

Removal of Ocular and Muscular Artifacts From Multi-Channel EEG Using Improved Spatial-Frequency Filtering

Wuxiang Shi
Yurong Li
Naiqing Cai
Rukai Chen
Wei Cao
Jixiang Li

Over recent decades, electroencephalogram (EEG) has become an essential tool in the field of clinical analysis and neurological disease research. However, EEG recordings are notably vulnerable to artifacts during acquisition, especially in clinical settings, which can significantly impede the accurate interpretation of neuronal activity. Blind source separation is currently the most popular method for EEG denoising, but most of the sources it separates often contain both artifacts and brain activity, which may lead to substantial information loss if handled improperly. In this paper, we introduce a dual-threshold denoising method combining spatial filtering with frequency-domain filtering to automatically eliminate electrooculogram (EOG) and electromyogram (EMG) artifacts from multi-channel EEG. The proposed method employs a fusion of second-order blind identification (SOBI) and canonical correlation analysis (CCA) to enhance source separation quality, followed by adaptive threshold to localize the artifact sources, and strict fixed threshold to remove strong artifact sources. Stationary wavelet transform (SWT) is utilized to decompose the weak artifact sources, with subsequent adjustment of wavelet coefficients in respective frequency bands tailored to the distinct characteristics of each artifact. The results of synthetic and real datasets show that our proposed method maximally retains the time-domain and frequency-domain information in the EEG during denoising. Compared with existing techniques, the proposed method achieves better denoising performance, which establishes a reliable foundation for subsequent clinical analyses.

Details DOI

AAAI Conference 2023 Conference Paper

PINAT: A Permutation INvariance Augmented Transformer for NAS Predictor

Shun Lu
Yu Hu
Peihao Wang
Yan Han
Jianchao Tan
Jixiang Li
Sen Yang
Ji Liu

Time-consuming performance evaluation is the bottleneck of traditional Neural Architecture Search (NAS) methods. Predictor-based NAS can speed up performance evaluation by directly predicting performance, rather than training a large number of sub-models and then validating their performance. Most predictor-based NAS approaches use a proxy dataset to train model-based predictors efficiently but suffer from performance degradation and generalization problems. We attribute these problems to the poor abilities of existing predictors to character the sub-models' structure, specifically the topology information extraction and the node feature representation of the input graph data. To address these problems, we propose a Transformer-like NAS predictor PINAT, consisting of a Permutation INvariance Augmentation module serving as both token embedding layer and self-attention head, as well as a Laplacian matrix to be the positional encoding. Our design produces more representative features of the encoded architecture and outperforms state-of-the-art NAS predictors on six search spaces: NAS-Bench-101, NAS-Bench-201, DARTS, ProxylessNAS, PPI, and ModelNet. The code is available at https://github.com/ShunLu91/PINAT.

PDF Details DOI

AAAI Conference 2023 Conference Paper

ProxyBO: Accelerating Neural Architecture Search via Bayesian Optimization with Zero-Cost Proxies

Yu Shen
Yang Li
Jian Zheng
Wentao Zhang
Peng Yao
Jixiang Li
Sen Yang
Ji Liu

Designing neural architectures requires immense manual efforts. This has promoted the development of neural architecture search (NAS) to automate the design. While previous NAS methods achieve promising results but run slowly, zero-cost proxies run extremely fast but are less promising. Therefore, it’s of great potential to accelerate NAS via those zero-cost proxies. The existing method has two limitations, which are unforeseeable reliability and one-shot usage. To address the limitations, we present ProxyBO, an efficient Bayesian optimization (BO) framework that utilizes the zero-cost proxies to accelerate neural architecture search. We apply the generalization ability measurement to estimate the fitness of proxies on the task during each iteration and design a novel acquisition function to combine BO with zero-cost proxies based on their dynamic influence. Extensive empirical studies show that ProxyBO consistently outperforms competitive baselines on five tasks from three public benchmarks. Concretely, ProxyBO achieves up to 5.41× and 3.86× speedups over the state-of-the-art approaches REA and BRP-NAS.

PDF Details DOI

NeurIPS Conference 2021 Conference Paper

TNASP: A Transformer-based NAS Predictor with a Self-evolution Framework

Shun Lu
Jixiang Li
Jianchao Tan
Sen Yang
Ji Liu

Predictor-based Neural Architecture Search (NAS) continues to be an important topic because it aims to mitigate the time-consuming search procedure of traditional NAS methods. A promising performance predictor determines the quality of final searched models in predictor-based NAS methods. Most existing predictor-based methodologies train model-based predictors under a proxy dataset setting, which may suffer from the accuracy decline and the generalization problem, mainly due to their poor abilities to represent spatial topology information of the graph structure data. Besides the poor encoding for spatial topology information, these works did not take advantage of the temporal information such as historical evaluations during training. Thus, we propose a Transformer-based NAS performance predictor, associated with a Laplacian matrix based positional encoding strategy, which better represents topology information and achieves better performance than previous state-of-the-art methods on NAS-Bench-101, NAS-Bench-201, and DARTS search space. Furthermore, we also propose a self-evolution framework that can fully utilize temporal information as guidance. This framework iteratively involves the evaluations of previously predicted results as constraints into current optimization iteration, thus further improving the performance of our predictor. Such framework is model-agnostic, thus can enhance performance on various backbone structures for the prediction task. Our proposed method helped us rank 2nd among all teams in CVPR 2021 NAS Competition Track 2: Performance Prediction Track.

PDF Details