ArticleProceedings of machine learning research2020
When Does Self-Supervision Help Graph Convolutional Networks?
Article in Proceedings of machine learning research, 2020. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 15 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
15 citing papers in PubMed.
- Self-supervised graph contrastive learning for scRNA-seq clustering.Journal of translational medicine · 2026Article
- Computational screening of oncogenic genetic variations in tumor suppressor proteins driving gastric cancer pathogenesis.PloS one · 2026Article
- Generative and Contrastive Self-Supervised Learning for Virulence Factor Identification Based on Protein-Protein Interaction Networks.Microorganisms · 2025Article
- Revealing Cortical Spreading Pathway of Neuropathological Events by Neural Optimal Mass Transport.IEEE transactions on medical imaging · 2025Article
- Enhancing atom mapping with multitask learning and symmetry-aware deep graph matching.Journal of cheminformatics · 2025Article
- Self-Supervised Based Multi-View Graph Presentation Learning for Drug-Drug Interaction Prediction.Transactions on artificial intelligence · 2025Article
- Better with Less: A Data-Active Perspective on Pre-Training Graph Neural Networks.Advances in neural information processing systems · 2023Article
- When to Pre-Train Graph Neural Networks? From Data Generation Perspective!KDD : proceedings. International Conference on Knowledge Discovery & Data Mining · 2023Article
- Graph Domain Adaptation via Theory-Grounded Spectral Regularization.... International Conference on Learning Representations · 2023Article
- Self-Supervised Learning of Graph Neural Networks: A Unified Review.IEEE transactions on pattern analysis and machine intelligence · 2023Article
- Self-Supervised Node Classification with Strategy and Actively Selected Labeled Set.Entropy (Basel, Switzerland) · 2022Article
- Cross-modality and self-supervised protein embedding for compound-protein affinity and contact prediction.Bioinformatics (Oxford, England) · 2022Article
- Bringing Your Own View: Graph Contrastive Learning without Prefabricated Data Augmentations.Proceedings of the ... International Conference on Web Search & Data Mining. International Conference on Web Search & Data Mining · 2022Article
- MoCL: Data-driven Molecular Fingerprint via Knowledge-aware Contrastive Learning from Molecular Graph.KDD : proceedings. International Conference on Knowledge Discovery & Data Mining · 2021Article
- Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future.Sensors (Basel, Switzerland) · 2021Review
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
4 authors.
Funding
Abstract
Self-supervision as an emerging technique has been employed to train convolutional neural networks (CNNs) for more transferrable, generalizable, and robust representation learning of images. Its introduction to graph convolutional networks (GCNs) operating on graph data is however rarely explored. In this study, we report the first systematic exploration and assessment of incorporating self-supervision into GCNs. We first elaborate three mechanisms to incorporate self-supervision into GCNs, analyze the limitations of pretraining & finetuning and self-training, and proceed to focus on multi-task learning. Moreover, we propose to investigate three novel self-supervised learning tasks for GCNs with theoretical rationales and numerical comparisons. Lastly, we further integrate multi-task self-supervision into graph adversarial training. Our results show that, with properly designed task forms and incorporation mechanisms, self-supervision benefits GCNs in gaining more generalizability and robustness. Our codes are available at https://github.com/Shen-Lab/SS-GCNs.
Identifiers
33283198PMC7714041What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.