# Every Node is Different: Dynamically Fusing Self-Supervised Tasks for Attributed Graph Clustering

arXiv: https://arxiv.org/abs/2401.06595 · HTML: https://mlsanity.com/paper/2401.06595/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 28 references that are in the map.
- First posted on arXiv 12 Jan 2024.

## Builds on (most cited first, 18 of 18)

- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [DeepWalk: Online Learning of Social Representations](https://mlsanity.com/paper/1403.6652/) (2014)
- [Variational Graph Auto-Encoders](https://mlsanity.com/paper/1611.07308/) (2016)
- [Deep Graph Infomax](https://mlsanity.com/paper/1809.10341/) (2018)
- [Unsupervised Deep Embedding for Clustering Analysis](https://mlsanity.com/paper/1511.06335/) (2015)
- [Graph Contrastive Learning with Adaptive Augmentation](https://mlsanity.com/paper/2010.14945/) (2020)
- [GraphMAE: Self-Supervised Masked Graph Autoencoders](https://mlsanity.com/paper/2205.10803/) (2022)
- [Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clustering](https://mlsanity.com/paper/1610.04794/) (2016)
- [Attributed Graph Clustering: A Deep Attentional Embedding Approach](https://mlsanity.com/paper/1906.06532/) (2019)
- [From Canonical Correlation Analysis to Self-supervised Graph Neural Networks](https://mlsanity.com/paper/2106.12484/) (2021)
- [Self-supervised Learning on Graphs: Contrastive, Generative,or Predictive](https://mlsanity.com/paper/2105.07342/) (2021)
- [When Does Self-Supervision Help Graph Convolutional Networks?](https://mlsanity.com/paper/2006.09136/) (2020)
- [Cluster-guided Contrastive Graph Clustering Network](https://mlsanity.com/paper/2301.01098/) (2023)
- [Automated Self-Supervised Learning for Graphs](https://mlsanity.com/paper/2106.05470/) (2021)
- [Self-Supervised Graph Representation Learning via Global Context Prediction](https://mlsanity.com/paper/2003.01604/) (2020)
- [Multi-task Self-supervised Graph Neural Networks Enable Stronger Task Generalization](https://mlsanity.com/paper/2210.02016/) (2022)
- [Self-supervised Contrastive Attributed Graph Clustering](https://mlsanity.com/paper/2110.08264/) (2021)
- [RWR-GAE: Random Walk Regularization for Graph Auto Encoders](https://mlsanity.com/paper/1908.04003/) (2019)

## Built on by (most cited first, 6 of 6)

- [Beyond the Academic Monoculture: A Unified Framework and Industrial Perspective for Attributed Graph Clustering](https://mlsanity.com/paper/2603.20829/) (2026)
- [Advancing Community Detection with Graph Convolutional Neural Networks: Bridging Topological and Attributive Cohesion](https://mlsanity.com/paper/2505.10197/) (2025)
- [Aggregation-aware MLP: An Unsupervised Approach for Graph Message-passing](https://mlsanity.com/paper/2507.20127/) (2025)
- [Attention Beyond Neighborhoods: Reviving Transformer for Graph Clustering](https://mlsanity.com/paper/2509.15024/) (2025)
- [Weighted Graph Clustering via Scale Contraction and Graph Structure Learning](https://mlsanity.com/paper/2601.17307/) (2026)
- [A Unified Perspective for Learning Graph Representations Across Multi-Level Abstractions](https://mlsanity.com/paper/2605.12685/) (2026)

## Abstract (arXiv)

Attributed graph clustering is an unsupervised task that partitions nodes into different groups. Self-supervised learning (SSL) shows great potential in handling this task, and some recent studies simultaneously learn multiple SSL tasks to further boost performance. Currently, different SSL tasks are assigned the same set of weights for all graph nodes. However, we observe that some graph nodes whose neighbors are in different groups require significantly different emphases on SSL tasks. In this paper, we propose to dynamically learn the weights of SSL tasks for different nodes and fuse the embeddings learned from different SSL tasks to boost performance. We design an innovative graph clustering approach, namely Dynamically Fusing Self-Supervised Learning (DyFSS). Specifically, DyFSS fuses features extracted from diverse SSL tasks using distinct weights derived from a gating network. To effectively learn the gating network, we design a dual-level self-supervised strategy that incorporates pseudo labels and the graph structure. Extensive experiments on five datasets show that DyFSS outperforms the state-of-the-art multi-task SSL methods by up to 8.66% on the accuracy metric. The code of DyFSS is available at: https://github.com/q086/DyFSS.