Jintang Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Jintang Li has a total of 79 co-authors. Here are the top co-authors by number of shared publications:
- Liang Chen
Sun Yat-sen University, Guangzhou, Guangdong, China
20 shared publications - Zibin Zheng
Sun Yat-Sen University, Guangzhou, China
18 shared publications Liang Chen
9 shared publications- Yuchang Zhu
Sun Yat-sen University, Guangzhou, Guangdong, China
8 shared publications Yuchang Zhu
6 shared publicationsZibin Zheng
6 shared publications
Latest Publications
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 3516-3526
One For All: Achieving Adaptive Graph Neural Networks via Mixture of Message Passing
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 3516-3526
Open AccessOne For All: Achieving Adaptive Graph Neural Networks via Mixture of Message Passing
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 2627-2637
Revisiting Graph Autoencoders as Implicit Contrastive Learners
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 2627-2637
Open AccessRevisiting Graph Autoencoders as Implicit Contrastive Learners
- 21 July 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 351
Attribute–structure decoupled self-supervised learning for graph anomaly detection
- 21 July 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 351
Attribute–structure decoupled self-supervised learning for graph anomaly detection
- 5 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (3) , 1946-1957
SaGIF: Improving Individual Fairness in Graph Neural Networks via Similarity Encoding
Individual fairness (IF) in graph neural networks (GNNs), which emphasizes the need for similar individuals should receive similar outcomes from GNNs, has been a critical issue. Despite its importance, research in this area has been largely unexplored in terms of (1) a clear understanding of what induces individual unfairness in GNNs and (2) a comprehensive consideration of identifying similar individuals. To bridge these gaps, we conduct a preliminary analysis to explore the underlying reason for individual unfairness and observe correlations between IF and similarity consistency, a concept introduced to evaluate the discrepancy in identifying similar individuals based on graph structure versus node features. Inspired by our observations, we introduce two metrics to assess individual similarity from two distinct perspectives: topology fusion and feature fusion. Building upon these metrics, we propose Similarity-aware GNNs for Individual Fairness, named SaGIF. The key insight behind SaGIF is the integration of individual similarities by independently learning similarity representations, leading to an improvement of IF in GNNs. Our experiments on several real-world datasets validate the effectiveness of our proposed metrics and SaGIF. Specifically, SaGIF consistently outperforms state-of-the-art IF methods while maintaining utility performance.
- 5 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (3) , 1946-1957
SaGIF: Improving Individual Fairness in Graph Neural Networks via Similarity Encoding
Individual fairness (IF) in graph neural networks (GNNs), which emphasizes the need for similar individuals should receive similar outcomes from GNNs, has been a critical issue. Despite its importance, research in this area has been largely unexplored in terms of (1) a clear understanding of what induces individual unfairness in GNNs and (2) a comprehensive consideration of identifying similar individuals. To bridge these gaps, we conduct a preliminary analysis to explore the underlying reason for individual unfairness and observe correlations between IF and similarity consistency, a concept introduced to evaluate the discrepancy in identifying similar individuals based on graph structure versus node features. Inspired by our observations, we introduce two metrics to assess individual similarity from two distinct perspectives: topology fusion and feature fusion. Building upon these metrics, we propose Similarity-aware GNNs for Individual Fairness, named SaGIF. The key insight behind SaGIF is the integration of individual similarities by independently learning similarity representations, leading to an improvement of IF in GNNs. Our experiments on several real-world datasets validate the effectiveness of our proposed metrics and SaGIF. Specifically, SaGIF consistently outperforms state-of-the-art IF methods while maintaining utility performance.
- 15 June 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 324
Capturing latent evolution in dynamic graph: A dual-view architecture from spectral perspective
- 15 June 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 324
Capturing latent evolution in dynamic graph: A dual-view architecture from spectral perspective
- 30 May 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 324
FairDLA: Improving the fairness-utility trade-off in graph neural networks via dual-level alignment
- 30 May 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 324
FairDLA: Improving the fairness-utility trade-off in graph neural networks via dual-level alignment
- 26 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 47 (9) , 7852-7866
Heterophily-Aware Representation Learning on Heterogeneous Graphs
Real-world graphs are typically complex, exhibiting heterogeneity in the global structure, as well as strong heterophily within local neighborhoods. While a growing body of literature has revealed the limitations of graph neural networks (GNNs) in handling homogeneous graphs with heterophily, little work has been conducted on investigating the heterophily properties in the context of heterogeneous graphs. To bridge this research gap, we identify the heterophily in heterogeneous graphs using metapaths and propose two practical metrics to quantitatively describe the levels of heterophily. Our empirical investigations on real-world heterogeneous graphs have revealed that heterogeneous graph neural networks (HGNNs), which inherit many mechanisms from GNNs designed for homogeneous graphs, struggle to generalize to heterogeneous graphs with heterophily or low levels of homophily. To address the challenge, we present Hetero$^{2}$ Net, a heterophily-aware HGNN that incorporates masked metapath prediction and masked label prediction tasks to effectively and flexibly handle both homophilic and heterophilic heterogeneous graphs. We evaluate the performance of Hetero$^{2}$ Net on five real-world heterogeneous graph benchmarks with varying levels of heterophily. Experimental results demonstrate that Hetero$^{2}$ Net outperforms strong baselines in the semi-supervised node classification task. In particular, Hetero$^{2}$ Net scales to an industrial-scale commercial graph with 13 M nodes and 157 M edges, demonstrating its effectiveness in handling large and complex heterogeneous graphs.- 26 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 47 (9) , 7852-7866
Heterophily-Aware Representation Learning on Heterogeneous Graphs
Real-world graphs are typically complex, exhibiting heterogeneity in the global structure, as well as strong heterophily within local neighborhoods. While a growing body of literature has revealed the limitations of graph neural networks (GNNs) in handling homogeneous graphs with heterophily, little work has been conducted on investigating the heterophily properties in the context of heterogeneous graphs. To bridge this research gap, we identify the heterophily in heterogeneous graphs using metapaths and propose two practical metrics to quantitatively describe the levels of heterophily. Our empirical investigations on real-world heterogeneous graphs have revealed that heterogeneous graph neural networks (HGNNs), which inherit many mechanisms from GNNs designed for homogeneous graphs, struggle to generalize to heterogeneous graphs with heterophily or low levels of homophily. To address the challenge, we present Hetero$^{2}$ Net, a heterophily-aware HGNN that incorporates masked metapath prediction and masked label prediction tasks to effectively and flexibly handle both homophilic and heterophilic heterogeneous graphs. We evaluate the performance of Hetero$^{2}$ Net on five real-world heterogeneous graph benchmarks with varying levels of heterophily. Experimental results demonstrate that Hetero$^{2}$ Net outperforms strong baselines in the semi-supervised node classification task. In particular, Hetero$^{2}$ Net scales to an industrial-scale commercial graph with 13 M nodes and 157 M edges, demonstrating its effectiveness in handling large and complex heterogeneous graphs.- Open Access
Are Large Language Models In-Context Graph Learners?
Large language models (LLMs) have demonstrated remarkable in-context reasoning capabilities across a wide range of tasks, particularly with unstructured inputs such as language or images. However, LLMs struggle to handle structured data, such as graphs, due to their lack of understanding of non-Euclidean structures. As a result, without additional fine-tuning, their performance significantly lags behind that of graph neural networks (GNNs) in graph learning tasks. In this paper, we show that learning on graph data can be conceptualized as a retrieval-augmented generation (RAG) process, where specific instances (e.g., nodes or edges) act as queries, and the graph itself serves as the retrieved context. Building on this insight, we propose a series of RAG frameworks to enhance the in-context learning capabilities of LLMs for graph learning tasks. Comprehensive evaluations demonstrate that our proposed RAG frameworks significantly improve LLM performance on graph-based tasks, particularly in scenarios where a pretrained LLM must be used without modification or accessed via an API.
Open AccessAre Large Language Models In-Context Graph Learners?
Large language models (LLMs) have demonstrated remarkable in-context reasoning capabilities across a wide range of tasks, particularly with unstructured inputs such as language or images. However, LLMs struggle to handle structured data, such as graphs, due to their lack of understanding of non-Euclidean structures. As a result, without additional fine-tuning, their performance significantly lags behind that of graph neural networks (GNNs) in graph learning tasks. In this paper, we show that learning on graph data can be conceptualized as a retrieval-augmented generation (RAG) process, where specific instances (e.g., nodes or edges) act as queries, and the graph itself serves as the retrieved context. Building on this insight, we propose a series of RAG frameworks to enhance the in-context learning capabilities of LLMs for graph learning tasks. Comprehensive evaluations demonstrate that our proposed RAG frameworks significantly improve LLM performance on graph-based tasks, particularly in scenarios where a pretrained LLM must be used without modification or accessed via an API.
- 23 January 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 311
Long-term evolutionary patterns matter: Self-supervised anomaly detection on dynamic graphs
- 23 January 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 311
Long-term evolutionary patterns matter: Self-supervised anomaly detection on dynamic graphs
- Open Access
Revisiting and Benchmarking Graph Autoencoders: A Contrastive Learning Perspective
Graph autoencoders (GAEs) are self-supervised learning models that can learn meaningful representations of graph-structured data by reconstructing the input graph from a low-dimensional latent space. Over the past few years, GAEs have gained significant attention in academia and industry. In particular, the recent advent of GAEs with masked autoencoding schemes marks a significant advancement in graph self-supervised learning research. While numerous GAEs have been proposed, the underlying mechanisms of GAEs are not well understood, and a comprehensive benchmark for GAEs is still lacking. In this work, we bridge the gap between GAEs and contrastive learning by establishing conceptual and methodological connections. We revisit the GAEs studied in previous works and demonstrate how contrastive learning principles can be applied to GAEs. Motivated by these insights, we introduce lrGAE (left-right GAE), a general and powerful GAE framework that leverages contrastive learning principles to learn meaningful representations. Our proposed lrGAE not only facilitates a deeper understanding of GAEs but also sets a new benchmark for GAEs across diverse graph-based learning tasks. The source code for lrGAE, including the baselines and all the code for reproducing the results, is publicly available at https://github.com/EdisonLeeeee/lrGAE.
Open AccessRevisiting and Benchmarking Graph Autoencoders: A Contrastive Learning Perspective
Graph autoencoders (GAEs) are self-supervised learning models that can learn meaningful representations of graph-structured data by reconstructing the input graph from a low-dimensional latent space. Over the past few years, GAEs have gained significant attention in academia and industry. In particular, the recent advent of GAEs with masked autoencoding schemes marks a significant advancement in graph self-supervised learning research. While numerous GAEs have been proposed, the underlying mechanisms of GAEs are not well understood, and a comprehensive benchmark for GAEs is still lacking. In this work, we bridge the gap between GAEs and contrastive learning by establishing conceptual and methodological connections. We revisit the GAEs studied in previous works and demonstrate how contrastive learning principles can be applied to GAEs. Motivated by these insights, we introduce lrGAE (left-right GAE), a general and powerful GAE framework that leverages contrastive learning principles to learn meaningful representations. Our proposed lrGAE not only facilitates a deeper understanding of GAEs but also sets a new benchmark for GAEs across diverse graph-based learning tasks. The source code for lrGAE, including the baselines and all the code for reproducing the results, is publicly available at https://github.com/EdisonLeeeee/lrGAE.