paper-with-me

Papers

Directed Graph Contrastive Learning

2021-12-01 · NeurIPS 2021 12 · Zekun Tong, Yuxuan Liang, Henghui Ding, Yongxing Dai, Xinke Li, Changhu Wang

Graph Contrastive Learning (GCL) has emerged to learn generalizable representations from contrastive views. However, it is still in its infancy with two concerns: 1) changing the graph structure through data augmentation to generate contrastive views may mislead the message passing scheme, as such graph changing action deprives the intrinsic graph structural information, especially the directional structure in directed graphs; 2) since GCL usually uses predefined contrastive views with hand-picking parameters, it does not take full advantage of the contrastive information provided by data augmentation, resulting in incomplete structure information for models learning. In this paper, we design a directed graph data augmentation method called Laplacian perturbation and theoretically analyze how it provides contrastive information without changing the directed graph structure. Moreover, we present a directed graph contrastive learning framework, which dynamically learns from all possible contrastive views generated by Laplacian perturbation. Then we train it using multi-task curriculum learning to progressively learn from multiple easy-to-difficult contrastive views. We empirically show that our model can retain more structural features of directed graphs than other GCL models because of its ability to provide complete contrastive information. Experiments on various benchmarks reveal our dominance over the state-of-the-art approaches.

📄 PDF Abstract BibTeX

Code (1)

flyingtango/digcl 공식 구현 pytorch

Tasks

Contrastive LearningData Augmentation

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

Signed Directed Graph Contrastive Learning with Laplacian Augmentation

2023-01-12 · Taewook Ko, Yoonhyuk Choi, Chong-Kwon Kim

Graph contrastive learning has become a powerful technique for several graph mining tasks. It learns discriminative representation from different perspectives of augmented graphs. Ubiquitous in our daily life, singed-dir…

Contrastive LearningGraph Mining

Toward General Digraph Contrastive Learning: A Dual Spatial Perspective

2025-10-18 · Zhengyu Wu, Daohan Su, Yang Zhang, Xunkai Li 외 arxiv

Graph Contrastive Learning (GCL) has emerged as a powerful tool for extracting consistent representations from graphs, independent of labeled information. However, existing methods predominantly focus on undirected graph…

Contrastive LearningNode ClassificationLink Prediction

Directed Link Prediction using GNN with Local and Global Feature Fusion

2025-06-25 · Yuyang Zhang, Xu Shen, Yu Xie, Ka-Chun Wong 외

Link prediction is a classical problem in graph analysis with many practical applications. For directed graphs, recently developed deep learning approaches typically analyze node similarities through contrastive learning…

Contrastive LearningGraph Neural NetworkLink Prediction

Dual-Center Graph Clustering with Neighbor Distribution

2025-07-18 · Enhao Cheng, Shoujia Zhang, Jianhua Yin, Li Jin 외 arxiv

Graph clustering is crucial for unraveling intricate data structures, yet it presents significant challenges due to its unsupervised nature. Recently, goal-directed clustering techniques have yielded impressive results, …

Representation LearningContrastive LearningGraph Clustering

Beyond DAGs: A Latent Partial Causal Model for Multimodal Learning

2024-02-09 · Yuhang Liu, Zhen Zhang, Dong Gong, Erdun Gao 외

Directed acyclic graphs (DAGs) are fundamental graph structures in causal modeling, but identifying the desired DAG from observational data often requires strong assumptions that may not hold in real-world scenarios, esp…

Contrastive LearningDisentanglementDomain GeneralizationFew-Shot Learning+1