Graph Communal Contrastive Learning

Li, Bolian; Jing, Baoyu; Tong, Hanghang

doi:10.1145/3485447.3512208

Cited by 33 publications

(16 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…AD-GCL [30] uses an adversarial graph augmentation strategy to avoid capturing redundant information during training. gCOOL [31] uses semantic preemptive community partitioning while comparing node similarity and community similarity to learn a more robust representation. Zhao et al [32] proposed a neural edge predictor that boosts intra-class edges and reduces inter-class edges in a given graph structure.…”

Section: Contrastive Learningmentioning

confidence: 99%

Hypergraph network embedding for community detection

Xiang,

You,

Wang

et al. 2024

J Supercomput

View full text Add to dashboard Cite

Using attribute graphs for node embedding to detect community structure has become a popular research topic. However, most of the existing algorithms mainly focus on the network structure and node features, which ignore the higher-order relationships between nodes. In addition, only adopting the original graph structure will suffer from sparsity problems, and will also result in sub-optimal node clustering performance. In this paper, we propose a hypergraph network embedding (HGNE) for community detection to solve the above problems. Firstly, we construct potential connections based on the shared feature information of the nodes. By fusing the original topology with feature-based potential connections, both the explicit and implicit relationships are encoded into the node representations, thus alleviating the sparsity problem. Secondly, for integrating the higher-order relationship, we adopt hypergraph convolution to encode the higherorder correlations. To constrain the quality of the node embedding, the spectral hypergraph embedding loss is utilized. Furthermore, we design a dual-contrast mechanism, which draws similar nodes closer by comparing the representations of different views. This mechanism can efficiently prevent multi-node classes from distorting less-node classes. Finally, the dual-contrast mechanism is jointly optimized with self-training clustering to obtain more robust node representations, thus improving the clustering results. Extensive experiments on five datasets indicate the superiority and effectiveness of HGNE.

show abstract

Section: Contrastive Learningmentioning

confidence: 99%

Hypergraph network embedding for community detection

Xiang,

You,

Wang

et al. 2024

J Supercomput

View full text Add to dashboard Cite

show abstract

“…(2) Information theory (IT) based methods: DGI (Velickovic et al 2019), gCooL (Li, Jing, and Tong 2022) and MGEDE (Yang et al 2023). (3) Graph structural learning (GSL) based methods: IDGL (Chen, Wu, and Zaki 2020), Pro-GNN (Jin et al 2020), GEN (Wang et al 2021), CoGSL (Liu et al 2022), SE-GSL (Zou et al 2023) and PROSE (Wang et al 2023).…”

Section: Experimental Setup Datasetsmentioning

confidence: 99%

“…The mainstream solution is training GNNs to aggregate neighborhood information for better node embeddings, e.g., GCN (Kipf and Welling 2017), GraphSAGE (Hamilton, Ying, and Leskovec 2017), GAT (Velickovic et al 2018) and GATv2 (Brody, Alon, and Yahav 2022). Some methods incorporate the information theory with GNNs, e.g., DGI (Velickovic et al 2019), gCool (Li, Jing, and Tong 2022) and MGEDE (Yang et al 2023). Recently, GSL techniques are used to enhance the node embeddings and become the dominant solution (Zhu et al 2021), which motivates our study of GSL based node classification.…”

Section: Related Workmentioning

confidence: 99%

Structural Entropy Based Graph Structure Learning for Node Classification

Duan,

Chen,

Liu

et al. 2024

AAAI

View full text Add to dashboard Cite

As one of the most common tasks in graph data analysis, node classification is frequently solved by using graph structure learning (GSL) techniques to optimize graph structures and learn suitable graph neural networks. Most of the existing GSL methods focus on fusing different structural features (basic views) extracted from the graph, but very little graph semantics, like hierarchical communities, has been incorporated. Thus, they might be insufficient when dealing with the graphs containing noises from real-world complex systems. To address this issue, we propose a novel and effective GSL framework for node classification based on the structural information theory. Specifically, we first prove that an encoding tree with the minimal structural entropy could contain sufficient information for node classification and eliminate redundant noise via the graph's hierarchical abstraction. Then, we provide an efficient algorithm for constructing the encoding tree to enhance the basic views. Combining the community influence deduced from the encoding tree and the prediction confidence of each view, we further fuse the enhanced views to generate the optimal structure. Finally, we conduct extensive experiments on a variety of datasets. The results demonstrate that our method outperforms the state-of-the-art competitors on effectiveness and robustness.

show abstract

“…The Thirty-Eighth AAAI Conference on Artificial Intelligence semantic errors (Li, Jing, and Tong 2022). Recently, BGRL (Thakoor et al 2021) and AFGRL (Lee, Lee, and Park 2022) propose to learn node embeddings without negative pairs for homogeneous graphs via bootstrapping.…”

Section: Introductionmentioning

confidence: 99%

Sterling: Synergistic Representation Learning on Bipartite Graphs

Jing,

Yan,

Ding

et al. 2024

AAAI

View full text Add to dashboard Cite

A fundamental challenge of bipartite graph representation learning is how to extract informative node embeddings. Self-Supervised Learning (SSL) is a promising paradigm to address this challenge. Most recent bipartite graph SSL methods are based on contrastive learning which learns embeddings by discriminating positive and negative node pairs. Contrastive learning usually requires a large number of negative node pairs, which could lead to computational burden and semantic errors. In this paper, we introduce a novel synergistic representation learning model (STERLING) to learn node embeddings without negative node pairs. STERLING preserves the unique local and global synergies in bipartite graphs. The local synergies are captured by maximizing the similarity of the inter-type and intra-type positive node pairs, and the global synergies are captured by maximizing the mutual information of co-clusters. Theoretical analysis demonstrates that STERLING could improve the connectivity between different node types in the embedding space. Extensive empirical evaluation on various benchmark datasets and tasks demonstrates the effectiveness of STERLING for extracting node embeddings.

show abstract

Graph Communal Contrastive Learning

Cited by 33 publications

References 38 publications

Hypergraph network embedding for community detection

Hypergraph network embedding for community detection

Structural Entropy Based Graph Structure Learning for Node Classification

Sterling: Synergistic Representation Learning on Bipartite Graphs

Contact Info

Product

Resources

About