Author name cluster

Chenyang Ge

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.

3 papers

1 author row

AAAI Conference 2026 Conference Paper

Gradient-Protected Value Decomposition for Cooperative Multi-Agent Reinforcement Learning

Jie Hou
Haowen Dou
Lujuan Dang
Liangjun Chen
Chenyang Ge

In recent years, deep multi-agent reinforcement learning (MARL) has demonstrated remarkable potential in solving complex cooperative tasks by enabling decentralized yet efficient coordination among agents. However, during decentralized training, agent policy updates induced by different joint action samples may conflict, leading to gradient interference that hinders convergence and the emergence of coordinated behavior. In this paper, we analyze and empirically validate the phenomenon of gradient interference. To address this, we then propose Gradient-Protected Value Decomposition (GPVD), a novel MARL framework that explicitly protects the gradient signals of optimal collaborative actions by suppressing the impact of interfering actions. GPVD employs a dynamic gradient protection mechanism that identifies optimal collaborative joint actions and reweights the loss to attenuate gradients from non-collaborative interfering actions. To effectively identify high-value collaborative actions, we apply SimHash-based state grouping to discover consistent collaboration patterns across similar states. Furthermore, a count-based intrinsic reward is incorporated to encourage exploration and improve the coverage of potentially optimal joint actions. Experiments on challenging multi-agent benchmarks demonstrate that GPVD achieves faster convergence, stronger coordination, and greater training stability compared to state-of-the-art value decomposition methods.

PDF Details DOI

EAAI Journal 2025 Journal Article

Memory guided representation learning for cross-domain face anti-spoofing

Pengchao Deng
Yanhui Zhou
Zhiheng Fu
Jian Liu
Shengjun Xu
Chenyang Ge
Farid Boussaid
Mohammed Bennamoun

Addressing generalized Face Anti-Spoofing is challenging due to the wide variety of spoofing techniques, variations in environmental conditions, and the diversity of devices used to capture images. Most approaches to enhancing the generalization ability of systems often manipulate image statistics to normalize images into a uniform representation space. However, this approach can restrict the capacity of the system to represent images accurately because image statistics vary significantly across different domains, each with unique characteristics. Recognizing that each source domain possesses distinct characteristics, we introduce an innovative approach based on memory guided representation learningto represent these characteristics in separate latent spaces. Specifically, we present a dual component framework comprising a Memory Guided Clustering Representation (MGCR)generator and a Memory Guided Mapping Representation (MGMR)classifier. Additionally, we create a memory bank filled with template and meta features, which are refined over time using a momentum update mechanism. The MGCR component employs clustering to allow new, unseen deep features close to the most similar template feature, thereby creating generalized clues for the generator. Meanwhile, the MGMR process leverages meta features to dynamically represent new domain spaces through linear combinations, bridging the divide between known and unknown domains. Our experimental results show that the proposed method significantly enhances the effectiveness under cross-domain scenarios, outperforming existing techniques. Especially in the “Leave One Out”setting, its average Half Total Error Rate exceeds that of other methods, reaching less than 10%.

Details DOI

EAAI Journal 2024 Journal Article

Multimodal contrastive learning for face anti-spoofing

Pengchao Deng
Chenyang Ge
Hao Wei
Yuan Sun
Xin Qiao

Multimodal face anti-spoofing systems adopt multiple sensor modalities, such as infrared, color, depth, and thermal, to distinguish between living and spoofing faces via complementary spoofing clues from each modality. One challenge is that when the multimodal face anti-spoofing system is placed in different environments, the sensor setup may not be unified, causing a certain sensor to be unavailable. To alleviate this issue, a two-stream face anti-spoofing method is proposed. The first stream focuses on extracting primary features from an available sensor by a baseline network. The second stream employs a multimodal contrastive learning strategy to acquire modality-agnostic and task-specific representations from another deployed sensor. Furthermore, a master–slave modulation fusion block is designed to effectively fuse features from the two streams. Experiments conducted on three public multimodal databases show the superior performance of the proposed method.

Details DOI