# Feature-Centric Unsupervised Node Representation Learning Without Homophily Assumption

arXiv: https://arxiv.org/abs/2512.15112 · HTML: https://mlsanity.com/paper/2512.15112/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 38 references that are in the map.
- First posted on arXiv 17 Dec 2025.

## Builds on (most cited first, 23 of 23)

- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [Fast Graph Representation Learning with PyTorch Geometric](https://mlsanity.com/paper/1903.02428/) (2019)
- [DeepWalk: Online Learning of Social Representations](https://mlsanity.com/paper/1403.6652/) (2014)
- [Simplifying Graph Convolutional Networks](https://mlsanity.com/paper/1902.07153/) (2019)
- [Variational Graph Auto-Encoders](https://mlsanity.com/paper/1611.07308/) (2016)
- [Graph Contrastive Learning with Augmentations](https://mlsanity.com/paper/2010.13902/) (2020)
- [Deep Graph Infomax](https://mlsanity.com/paper/1809.10341/) (2018)
- [Predict then Propagate: Graph Neural Networks meet Personalized PageRank](https://mlsanity.com/paper/1810.05997/) (2018)
- [Contrastive Multi-View Representation Learning on Graphs](https://mlsanity.com/paper/2006.05582/) (2020)
- [Adaptive Universal Generalized PageRank Graph Neural Network](https://mlsanity.com/paper/2006.07988/) (2020)
- [GraphMAE: Self-Supervised Masked Graph Autoencoders](https://mlsanity.com/paper/2205.10803/) (2022)
- [Graph Neural Networks for Graphs with Heterophily: A Survey](https://mlsanity.com/paper/2202.07082/) (2022)
- [GraphMAE2: A Decoding-Enhanced Masked Self-Supervised Graph Learner](https://mlsanity.com/paper/2304.04779/) (2023)
- [A Survey on Heterogeneous Graph Embedding: Methods, Techniques, Applications and Sources](https://mlsanity.com/paper/2011.14867/) (2020)
- [Deep Clustering via Joint Convolutional Autoencoder Embedding and Relative Entropy Minimization](https://mlsanity.com/paper/1704.06327/) (2017)
- [Beyond Smoothing: Unsupervised Graph Representation Learning with Edge Heterophily Discriminating](https://mlsanity.com/paper/2211.14065/) (2022)
- [Multi-task Self-supervised Graph Neural Networks Enable Stronger Task Generalization](https://mlsanity.com/paper/2210.02016/) (2022)
- [SLIC: Self-Supervised Learning with Iterative Clustering for Human Action Videos](https://mlsanity.com/paper/2206.12534/) (2022)
- [HypeBoy: Generative Self-Supervised Representation Learning on Hypergraphs](https://mlsanity.com/paper/2404.00638/) (2024)
- [Feature Distribution on Graph Topology Mediates the Effect of Graph Convolution: Homophily Perspective](https://mlsanity.com/paper/2402.04621/) (2024)
- [Graph Contrastive Learning under Heterophily via Graph Filters](https://mlsanity.com/paper/2303.06344/) (2023)
- ['Hello, World!': Making GNNs Talk with LLMs](https://mlsanity.com/paper/2505.20742/) (2025)
- [VideoClusterNet: Self-Supervised and Adaptive Face Clustering For Videos](https://mlsanity.com/paper/2407.12214/) (2024)

## Abstract (arXiv)

Unsupervised node representation learning aims to obtain meaningful node embeddings without relying on node labels. To achieve this, graph convolution, which aggregates information from neighboring nodes, is commonly employed to encode node features and graph topology. However, excessive reliance on graph convolution can be suboptimal-especially in non-homophilic graphs-since it may yield unduly similar embeddings for nodes that differ in their features or topological properties. As a result, adjusting the degree of graph convolution usage has been actively explored in supervised learning settings, whereas such approaches remain underexplored in unsupervised scenarios. To tackle this, we propose FUEL, which adaptively learns the adequate degree of graph convolution usage by aiming to enhance intra-class similarity and inter-class separability in the embedding space. Since classes are unknown, FUEL leverages node features to identify node clusters and treats these clusters as proxies for classes. Through extensive experiments using 15 baseline methods and 14 benchmark datasets, we demonstrate the effectiveness of FUEL in downstream tasks, achieving state-of-the-art performance across graphs with diverse levels of homophily.