# Graph InfoClust: Leveraging cluster-level node information for unsupervised graph representation learning

arXiv: https://arxiv.org/abs/2009.06946 · HTML: https://mlsanity.com/paper/2009.06946/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Sep 2020.

## Built on by (most cited first, 30 of 35)

- [Graph Self-Supervised Learning: A Survey](https://mlsanity.com/paper/2103.00111/) (2021)
- [Self-supervised Learning on Graphs: Contrastive, Generative,or Predictive](https://mlsanity.com/paper/2105.07342/) (2021)
- [A Unified Lottery Ticket Hypothesis for Graph Neural Networks](https://mlsanity.com/paper/2102.06790/) (2021)
- [Neural Link Prediction with Walk Pooling](https://mlsanity.com/paper/2110.04375/) (2021)
- [Variational Graph Normalized Auto-Encoders](https://mlsanity.com/paper/2108.08046/) (2021)
- [Towards Graph Contrastive Learning: A Survey and Beyond](https://mlsanity.com/paper/2405.11868/) (2024)
- [Edge: Enriching Knowledge Graph Embeddings with External Text](https://mlsanity.com/paper/2104.04909/) (2021)
- [The Snowflake Hypothesis: Training Deep GNN with One Node One Receptive field](https://mlsanity.com/paper/2308.10051/) (2023)
- [Link-Backdoor: Backdoor Attack on Link Prediction via Node Injection](https://mlsanity.com/paper/2208.06776/) (2022)
- [GenURL: A General Framework for Unsupervised Representation Learning](https://mlsanity.com/paper/2110.14553/) (2021)
- [USER: Unsupervised Structural Entropy-based Robust Graph Neural Network](https://mlsanity.com/paper/2302.05889/) (2023)
- [Link Prediction with Contextualized Self-Supervision](https://mlsanity.com/paper/2201.10069/) (2022)
- [Memory-Associated Differential Learning](https://mlsanity.com/paper/2102.05246/) (2021)
- [Unsupervised Deep Manifold Attributed Graph Embedding](https://mlsanity.com/paper/2104.13048/) (2021)
- [Learning Compact Representations of Neural Networks using DiscriminAtive Masking (DAM)](https://mlsanity.com/paper/2110.00684/) (2021)
- [Contrastive Representation Learning Based on Multiple Node-centered Subgraphs](https://mlsanity.com/paper/2308.16441/) (2023)
- [Graph Prompting for Graph Learning Models: Recent Advances and Future Directions](https://mlsanity.com/paper/2506.08326/) (2025)
- [Graph Representation Learning via Contrasting Cluster Assignments](https://mlsanity.com/paper/2112.07934/) (2021)
- [Graph Perceiver IO: A General Architecture for Graph Structured Data](https://mlsanity.com/paper/2209.06418/) (2022)
- [PHLP: Sole Persistent Homology for Link Prediction - Interpretable Feature Extraction](https://mlsanity.com/paper/2404.15225/) (2024)
- [Self-Supervised Deep Graph Embedding with High-Order Information Fusion for Community Discovery](https://mlsanity.com/paper/2102.03302/) (2021)
- [Barlow Graph Auto-Encoder for Unsupervised Network Embedding](https://mlsanity.com/paper/2110.15742/) (2021)
- [AutoHEnsGNN: Winning Solution to AutoGraph Challenge for KDD Cup 2020](https://mlsanity.com/paper/2111.12952/) (2021)
- [Graph Self-Contrast Representation Learning](https://mlsanity.com/paper/2309.02304/) (2023)
- [BHGNN-RT: Network embedding for directed heterogeneous graphs](https://mlsanity.com/paper/2311.14404/) (2023)
- [Introducing New Node Prediction in Graph Mining: Predicting All Links from Isolated Nodes with Graph Neural Networks](https://mlsanity.com/paper/2401.05468/) (2024)
- [TopER: Topological Embeddings in Graph Representation Learning](https://mlsanity.com/paper/2410.01778/) (2024)
- [Pointspectrum: Equivariance Meets Laplacian Filtering for Graph Representation Learning](https://mlsanity.com/paper/2109.02358/) (2021)
- [HeMI: Multi-view Embedding in Heterogeneous Graphs](https://mlsanity.com/paper/2109.07008/) (2021)
- [An unsupervised cluster-level based method for learning node representations of heterogeneous graphs in scientific papers](https://mlsanity.com/paper/2203.16751/) (2022)

## Abstract (arXiv)

Unsupervised (or self-supervised) graph representation learning is essential to facilitate various graph data mining tasks when external supervision is unavailable. The challenge is to encode the information about the graph structure and the attributes associated with the nodes and edges into a low dimensional space. Most existing unsupervised methods promote similar representations across nodes that are topologically close. Recently, it was shown that leveraging additional graph-level information, e.g., information that is shared among all nodes, encourages the representations to be mindful of the global properties of the graph, which greatly improves their quality. However, in most graphs, there is significantly more structure that can be captured, e.g., nodes tend to belong to (multiple) clusters that represent structurally similar nodes. Motivated by this observation, we propose a graph representation learning method called Graph InfoClust (GIC), that seeks to additionally capture cluster-level information content. These clusters are computed by a differentiable K-means method and are jointly optimized by maximizing the mutual information between nodes of the same clusters. This optimization leads the node representations to capture richer information and nodal interactions, which improves their quality. Experiments show that GIC outperforms state-of-art methods in various downstream tasks (node classification, link prediction, and node clustering) with a 0.9% to 6.1% gain over the best competing approach, on average.