33 citations · 47 across the 21 of their papers we have counts for
21 papers
Node-to-Neighborhood Semantic Consistency: Text-Topology Alignment for TAGs Anomaly Detection
Bochen Lin, Jianxiang Yu, Jiayi Wu +3
Graph anomaly detection (GAD) on text-attributed graphs (TAGs) is vital for applications such as fraud detection and academic integrity verification. Existing approaches generally…
Skill is Not One-Size-Fits-All: Model-Aware Skill Alignment for LLM Agents
Jianxiang Yu, Jiapeng Zhu, Bochen Lin +3
LLM agents increasingly retrieve externally curated skills-procedural instructions retrieved at decision time-to improve performance on long-horizon interactive tasks. Existing ski…
Skill0.5: Joint Skill Internalization and Utilization for Out-of-Distribution Generalization in Agentic Reinforcement Learning
Jiapeng Zhu, Jianxiang Yu, Yibo Zhao +5
Equipping large language models with explicit skills has emerged as a promising paradigm for enabling autonomous agents to solve complex tasks. Agent skills can be inherently divid…
Beyond Chunk-Local Extraction: Cross-Chunk Graph Augmentation for GraphRAG
Jiaming Zhang, Yibo Zhao, Jing Yu +2
GraphRAG extends retrieval-augmented generation by organizing corpora as explicit knowledge graphs, enabling graph-based retrieval for complex question answering. However, existing…
APEX: Academic Poster Editing Agentic Expert
Chengxin Shi, Qinnan Cai, Zeyuan Chen +5
Designing academic posters is a labor-intensive process requiring the precise balance of high-density content and sophisticated layout. While existing paper-to-poster generation me…
Breaking the Cloak! Unveiling Chinese Cloaked Toxicity with Homophone Graph and Toxic Lexicon
Xuchen Ma, Jianxiang Yu, Wenming Shao +2
Social media platforms have experienced a significant rise in toxic content, including abusive language and discriminatory remarks, presenting growing challenges for content modera…
Relation-Aware Graph Foundation Model
Jianxiang Yu, Jiapeng Zhu, Hao Qian +4
In recent years, large language models (LLMs) have demonstrated remarkable capability to generalize across diverse natural language processing tasks, inspiring the development of g…
Hierarchical Vector Quantized Graph Autoencoder with Annealing-Based Code Selection
Long Zeng, Jianxiang Yu, Jiapeng Zhu +2
Graph self-supervised learning has gained significant attention recently. However, many existing approaches heavily depend on perturbations, and inappropriate perturbations may cor…
SEAGraph: Unveiling the Whole Story of Paper Review Comments
Jianxiang Yu, Jiaqi Tan, Zichen Ding +7
Peer review, as a cornerstone of scientific research, ensures the integrity and quality of scholarly work by providing authors with objective feedback for refinement. However, in t…
Can Large Language Models Act as Ensembler for Multi-GNNs?
Hanqi Duan, Yao Cheng, Jianxiang Yu +2
Graph Neural Networks (GNNs) have emerged as powerful models for learning from graph-structured data. However, GNNs lack the inherent semantic understanding capability of rich text…
RELIEF: Reinforcement Learning Empowered Graph Feature Prompt Tuning
Jiapeng Zhu, Zichen Ding, Jianxiang Yu +3
The advent of the "pre-train, prompt" paradigm has recently extended its generalization ability and data efficiency to graph representation learning, following its achievements in…
Boosting Graph Foundation Model from Structural Perspective
Yao Cheng, Yige Zhao, Jianxiang Yu +1
Graph foundation models have recently attracted significant attention due to its strong generalizability. Although existing methods resort to language models to learn unified seman…
Automated Peer Reviewing in Paper SEA: Standardization, Evaluation, and Analysis
Jianxiang Yu, Zichen Ding, Jiaqi Tan +10
In recent years, the rapid increase in scientific papers has overwhelmed traditional review mechanisms, resulting in varying quality of publications. Although existing methods have…
Improving Graph Out-of-distribution Generalization Beyond Causality
Can Xu, Yao Cheng, Jianxiang Yu +4
Existing methods for graph out-of-distribution (OOD) generalization primarily rely on empirical studies on synthetic datasets. Such approaches tend to overemphasize the causal rela…
A Survey on Learning from Graphs with Heterophily: Recent Advances and Future Directions
Chenghua Gong, Yao Cheng, Jianxiang Yu +4
Graphs are structured data that models complex relations between real-world entities. Heterophilic graphs, where linked nodes are prone to be with different labels or dissimilar fe…
Resist Label Noise with PGM for Graph Neural Networks
Qingqing Ge, Jianxiang Yu, Zeyuan Zhao +1
While robust graph neural networks (GNNs) have been widely studied for graph perturbation and attack, those for label noise have received significantly less attention. Most existin…
Variational Graph Autoencoder for Heterogeneous Information Networks with Missing and Inaccurate Attributes
Yige Zhao, Jianxiang Yu, Yao Cheng +4
Heterogeneous Information Networks (HINs), which consist of various types of nodes and edges, have recently demonstrated excellent performance in graph mining. However, most existi…
Context-aware Session-based Recommendation with Graph Neural Networks
Zhihui Zhang, JianXiang Yu, Xiang Li
Session-based recommendation (SBR) is a task that aims to predict items based on anonymous sequences of user behaviors in a session. While there are methods that leverage rich cont…
Self-Pro: A Self-Prompt and Tuning Framework for Graph Neural Networks
Chenghua Gong, Xiang Li, Jianxiang Yu +3
Graphs have become an important modeling tool for web applications, and Graph Neural Networks (GNNs) have achieved great success in graph representation learning. However, the perf…
Leveraging Large Language Models for Node Generation in Few-Shot Learning on Text-Attributed Graphs
Jianxiang Yu, Yuxiang Ren, Chenghua Gong +3
Text-attributed graphs have recently garnered significant attention due to their wide range of applications in web domains. Existing methodologies employ word embedding models for…
Heterogeneous Graph Contrastive Learning with Meta-path Contexts and Adaptively Weighted Negative Samples
Jianxiang Yu, Qingqing Ge, Xiang Li +1
Heterogeneous graph contrastive learning has received wide attention recently. Some existing methods use meta-paths, which are sequences of object types that capture semantic relat…