Author name cluster

Chunchun Chen

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

YNIMG Journal 2026 Journal Article

Disentangling computational and neural mechanisms of evaluation direction in value-based decision-making

Chunchun Chen
Xin Lin
Yilin Yang
Jianping Huang

Most value-based decision-making research rests on the implicit assumption that individuals typically evaluate options based on subjective preferences, favoring high-value alternatives. However, in certain contexts, the focus of information evaluation during decision-making processes may shift toward low-value evidence rather than high-value evidence. These two evaluation directions may dynamically alternate within a single decision episode to support the final decision. Yet prior studies have rarely disentangled these evaluation modes, which has limited our understanding of the cognitive and neural dynamics underlying changes in evaluation direction. This study recruited 36 participants and employed a value-based binary choice paradigm manipulating evaluation direction via task framing. While decision outcomes did not significantly differ across conditions, distinct computational and neural signatures emerged. Specifically, behavioral indicators and a hierarchical drift diffusion model (HDDM) revealed that low-value-directed evaluations were associated with longer reaction times, slower evidence accumulation, and higher decision thresholds, indicating increased deliberation. Electroencephalography (EEG) results further showed enhanced N200 and centro-parietal positivity (CPP) amplitudes in the low-value condition, reflecting greater value conflict and diminished value integration efficiency; simultaneously, increased alpha and beta desynchronization suggested heightened demand of attentional resources and stronger decision commitment. Together, these results demonstrate that value evaluation direction modulates the decision-making process across distinct temporal periods-from early value conflict to late-stage evidence accumulation and action preparation, revealing the underlying mechanisms of humans' flexible value encoding and providing a new methodological framework for analyzing multi-level value construction.

Details DOI

AAAI Conference 2026 Conference Paper

Edge Self-Adversarial Augmentation Enhances Graph Contrastive Learning Against Neighborhood Inconsistency

Chunchun Chen
Xing Wei
Jiayi Yang
Chenrun Wang
Yiwei Fu
Yuxing Zhang
Xin Sun
Rui Fan

Recent studies have shown that unsupervised graph contrastive learning (GCL) is vulnerable to adversarial attacks. Automatic adversarial augmentation techniques are proposed to improve both the effectiveness and robustness of GCL. Existing methods typically regard unsupervised contrastive loss as the adversarial goal, essentially aiming to maximize inter-view instance-wise discrepancies between adversarial and original views. However, such attacks overlook intra-view neighborhood inconsistency, which hinders the robustness of GCL models against local neighborhood noises, resulting in performance degradation on low-homophily graphs. To tackle this issue, we propose a novel adversarial contrastive paradigm, named Edge self-aDversarial Augmentation for Graph Contrastive Learning (EDA-GCL). We theoretically establish that the adversarial objective of the intra-view neighborhood is equivalent to maximizing the discrepancy between bidirectional edge features. Hence, we build our adversarial framework based on edge self-adversarial learning. It generates pairwise adversarial augmentations from the original view by learning distinct neighborhood connectivity structures. The learned pairwise adversarial views are utilized for GCL model training in the minimization stage. Notably, this edge-level adversarial approach reduces the computational complexity to the level of the edge number. Experiments on various graph tasks and complex noise scenarios demonstrate the superiority and robustness of our EDA-GCL.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Preference-driven Knowledge Distillation for Few-shot Node Classification

Xing Wei
Chunchun Chen
Rui Fan
Xiaofeng Cao
Sourav Medya
Wei Ye

Graph neural networks (GNNs) can efficiently process text-attributed graphs (TAGs) due to their message-passing mechanisms, but their training heavily relies on the human-annotated labels. Moreover, the complex and diverse local topologies of nodes of real-world TAGs make it challenging for a single mechanism to handle. Large language models (LLMs) perform well in zero-/few-shot learning on TAGs but suffer from a scalability challenge. Therefore, we propose a preference-driven knowledge distillation (PKD) framework to synergize the complementary strengths of LLMs and various GNNs for few-shot node classification. Specifically, we develop a GNN-preference-driven node selector that effectively promotes prediction distillation from LLMs to teacher GNNs. To further tackle nodes' intricate local topologies, we develop a node-preference-driven GNN selector that identifies the most suitable teacher GNN for each node, thereby facilitating tailored knowledge distillation from teacher GNNs to the student GNN. Extensive experiments validate the efficacy of our proposed framework in few-shot node classification on real-world TAGs. Our code can be available at.

PDF Details