# There is more to graphs than meets the eye: Learning universal features with self-supervision

arXiv: https://arxiv.org/abs/2305.19871 · HTML: https://mlsanity.com/paper/2305.19871/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 42 references that are in the map.
- First posted on arXiv 31 May 2023.

## Builds on (most cited first, 30 of 34)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Deep Graph Infomax](https://mlsanity.com/paper/1809.10341/) (2018)
- [Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks](https://mlsanity.com/paper/1810.02244/) (2018)
- [OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework](https://mlsanity.com/paper/2202.03052/) (2022)
- [Graph Neural Networks for Social Recommendation](https://mlsanity.com/paper/1902.07243/) (2019)
- [Recipe for a General, Powerful, Scalable Graph Transformer](https://mlsanity.com/paper/2205.12454/) (2022)
- [On the Bottleneck of Graph Neural Networks and its Practical Implications](https://mlsanity.com/paper/2006.05205/) (2020)
- [Heterogeneous Graph Transformer](https://mlsanity.com/paper/2003.01332/) (2020)
- [Graph Transformer Networks](https://mlsanity.com/paper/1911.06455/) (2019)
- [Rethinking Graph Transformers with Spectral Attention](https://mlsanity.com/paper/2106.03893/) (2021)
- [VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text](https://mlsanity.com/paper/2104.11178/) (2021)
- [Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks](https://mlsanity.com/paper/2206.08916/) (2022)
- [Self-supervised Graph Learning for Recommendation](https://mlsanity.com/paper/2010.10783/) (2020)
- [Graph Self-Supervised Learning: A Survey](https://mlsanity.com/paper/2103.00111/) (2021)
- [Revisiting Self-Supervised Visual Representation Learning](https://mlsanity.com/paper/1901.09005/) (2019)
- [A Cookbook of Self-Supervised Learning](https://mlsanity.com/paper/2304.12210/) (2023)
- [Self-Supervised Learning of Graph Neural Networks: A Unified Review](https://mlsanity.com/paper/2102.10757/) (2021)
- [Motif-based Graph Self-Supervised Learning for Molecular Property Prediction](https://mlsanity.com/paper/2110.00987/) (2021)
- [mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video](https://mlsanity.com/paper/2302.00402/) (2023)
- [NAGphormer: A Tokenized Graph Transformer for Node Classification in Large Graphs](https://mlsanity.com/paper/2206.04910/) (2022)
- [Towards artificial general intelligence via a multimodal foundation model](https://mlsanity.com/paper/2110.14378/) (2021)
- [Combinatorial Optimization with Physics-Inspired Graph Neural Networks](https://mlsanity.com/paper/2107.01188/) (2021)
- [Molecular graph generation with Graph Neural Networks](https://mlsanity.com/paper/2012.07397/) (2020)
- [Automated Self-Supervised Learning for Graphs](https://mlsanity.com/paper/2106.05470/) (2021)
- [Learning to Extrapolate Knowledge: Transductive Few-shot Out-of-Graph Link Prediction](https://mlsanity.com/paper/2006.06648/) (2020)
- [Multi-Modal Graph Neural Network for Joint Reasoning on Vision and Scene Text](https://mlsanity.com/paper/2003.13962/) (2020)

## Built on by (most cited first, 1 of 1)

- [Generalist Multimodal AI: A Review of Architectures, Challenges and Opportunities](https://mlsanity.com/paper/2406.05496/) (2024)

## Abstract (arXiv)

We study the problem of learning features through self-supervision that are generalisable to multiple graphs. State-of-the-art graph self-supervision restricts training to only one graph, resulting in graph-specific models that are incompatible with different but related graphs. We hypothesize that training with more than one graph that belong to the same family can improve the quality of the learnt representations. However, learning universal features from disparate node/edge features in different graphs is non-trivial. To address this challenge, we first homogenise the disparate features with graph-specific encoders that transform the features into a common space. A universal representation learning module then learns generalisable features on this common space. We show that compared to traditional self-supervision with one graph, our approach results in (1) better performance on downstream node classification, (2) learning features that can be re-used for unseen graphs of the same family, (3) more efficient training and (4) compact yet generalisable models. We also show ability of the proposed framework to deliver these benefits for relatively larger graphs. In this paper, we present a principled way to design foundation graph models that learn from more than one graph in an end-to-end manner, while bridging the gap between self-supervised and supervised performance.