Research map / Graph learning / Graph self-supervised learning
Brain and biological graph learning
Apply graph learning to brain networks and biological data.
78 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2017–2026) · an approach in Graph self-supervised learning, keyword cluster “classification · semi supervised · representation”
State History Tried Checklist Preprints Who Export
Where it stands
Not enough benchmark data Fewer than four papers report the same benchmark, so there is no record to follow.
17 papers in 2023–24 and 41 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic grew, from 4.9% to 7.0%.
How this is decided
A benchmark is tracked when at least four papers of this approach report their own method on the same dataset and metric in at least two different years. Its record is the best number reported up to 2024 compared with the best reported in 2025–26: still improving means at least 1% better, flat means at most 0.2% better with at least two papers from 2025–26 trying. Numbers on a different scale from the rest (a fraction among percentages) and far outliers are left out. Results come from different papers with different setups, so they are signals, not head-to-head comparisons. The share of papers is counted at ICML, NeurIPS, ICLR, CVPR and AAAI.
How it got here
Most cited paper of each year
- 2017 · SnapNETS: Automatic Segmentation of Network Sequences with Node Labels (AAAI 2017 · 7 citations)
- 2018 · Deep Lesion Graphs in the Wild: Relationship Learning and Organization of Significant Radiology Image Findings in a Diverse Large-Scale Lesion Database (CVPR 2018 · 132 citations)
- 2019 · Adaptively Connected Neural Networks (CVPR 2019 · 69 citations)
- 2020 · Learning the Graphical Structure of Electronic Health Records with Graph Convolutional Transformer (AAAI 2020 · 250 citations)
- 2021 · Quantifying Explainers of Graph Neural Networks in Computational Pathology (CVPR 2021 · 74 citations)
- 2022 · ZINB-Based Graph Embedding Autoencoder for Single-Cell RNA-Seq Interpretations (AAAI 2022 · 111 citations)
- 2023 · Self-Supervised Graph Learning for Long-Tailed Cognitive Diagnosis (AAAI 2023 · 42 citations)
- 2024 · Cell Graph Transformer for Nuclei Classification (AAAI 2024 · 11 citations)
- 2025 · CG-TGAN: Conditional Generative Adversarial Networks with Graph Neural Networks for Tabular Data Synthesizing (AAAI 2025 · 8 citations)
- 2026 · Learning Structurally Stabilized Representations for Lossless DNA Storage (AAAI 2026 · 2 citations)
Earliest papers here
- SnapNETS: Automatic Segmentation of Network Sequences with Node Labels (AAAI 2017 · 7 citations)
- Deep Lesion Graphs in the Wild: Relationship Learning and Organization of Significant Radiology Image Findings in a Diverse Large-Scale Lesion Database (CVPR 2018 · 132 citations)
- Multi-View Multi-Graph Embedding for Brain Network Clustering Analysis (AAAI 2018 · 48 citations)
What has been tried
43 papers here report 447 measured changes (a component added, removed or swapped, compared with a baseline): helped 68%, no clear effect 8%, hurt 19%, mixed 4%. Papers mostly publish changes that helped, so "helped" is over-represented.
Ablations in recent papers
| What was changed | Measured on | Result | Effect | Paper |
|---|---|---|---|---|
| Use GCN pretraining instead of ImageNet pretraining | PanNuke · F_avg | 0.344 -> 0.558 | Helped | Cell Graph Transformer for Nuclei Classification (AAAI 2024 · 11 citations) |
| add gene graph reconstruction loss Lg | AVG (all datasets) · NMI | 0.8104 -> 0.8226 | Helped | Unsupervised Gene-Cell Collective Representation Learning with Optimal Transport (AAAI 2024 · 9 citations) |
| Use a conditional node | tabular data synthesis; seven datasets · machine-learning utility | Mixed | CG-TGAN: Conditional Generative Adversarial Networks with Graph Neural Networks for Tabular Data Synthesizing (AAAI 2025 · 8 citations) | |
| Increase the number of nodes per cycle | Tree-Cycles (TC) · Correctness | Helped | Robust Stochastic Graph Generator for Counterfactual Explanations (AAAI 2024 · 5 citations) | |
| Add Gene Channel Attention (GCA) | Simulated datasets · Avg MSE | 0.3904 ± 0.0087 -> 0.3865 ± 0.0070 | Helped | DUSTED: Dual-Attention Enhanced Spatial Transcriptomics Denoiser (AAAI 2025 · 3 citations) |
| add DR-Label to 3d-Graphormer | OC20 IS2RE 10k validation, Average · MAE (meV) | 695 -> 689 | Helped | DR-Label: Label Deconstruction and Reconstruction of GNN Models for Catalysis Systems (AAAI 2024 · 3 citations) |
| replace hierarchical message passing with a single message-passing operation per block | GlycanML · weighted mean rank | 2.56 -> 11.22 | Hurt | Modeling All-Atom Glycan Structures via Hierarchical Message Passing and Multi-Scale Pre-training (ICML 2025 · 1 citation) |
| Add 5% labeled data | HeterITE-50, HeterITE-100, and HeterITE-500 · Recall@1 | 0.718 -> 0.820; 0.690 -> 0.731; 0.627 -> 0.667 | Helped | DeepITE: Designing Variational Graph Autoencoders for Intervention Target Estimation (NeurIPS 2024 · 1 citation) |
| Add concatenation and standardization to model complete gene-gene relationships | Baron Mouse, Zeisel, Baron Human · ARI | 0.625±0.001 -> 0.827±0.093; 0.789±0.000 -> 0.902±0.000; 0.805±0.000 -> 0.823±0.000 | Helped | Gene-Gene Relationship Modeling Based on Genetic Evidence for Single-Cell RNA-Seq Data Imputation (NeurIPS 2024 · 1 citation) |
| Use self-attention mapping instead of direct mapping | fault location · accuracy | Helped | Disentangled Table-Graph Representation for Interpretable Transmission Line Fault Location (AAAI 2025 · 0 citations) | |
| add age parameter θ | Cannabis · AUC | 0.49 -> 0.80 | Helped | NeuroTree: Hierarchical Functional Brain Pathway Decoding for Mental Health Disorders (ICML 2025 · 0 citations) |
| Replace original masked modeling with masked gate modeling (MGM) in latent space, masking ratio 0.3 | QoR prediction (10 designs) · NDCG@3 | 0.153 -> 0.338 | Helped | Circuit Representation Learning with Masked Gate Modeling and Verilog-AIG Alignment (ICLR 2025 · 0 citations) |
What reviewers will expect
Datasets and baselines named in the 15 papers of this approach from 2025–2026 that have a full-text summary. Leaving out the common ones is a frequent review question.
Datasets
- ADNI · 3 of 15 papers
- ABIDE · 2 of 15 papers
- ADHD-200 · 2 of 15 papers
Baselines
- GAT · 4 of 15 papers
- BrainGNN · 3 of 15 papers
- Random Forest · 2 of 15 papers
- GCN · 2 of 15 papers
- Graphormer · 2 of 15 papers
- Graph Transformer · 2 of 15 papers
- BRAINNETTF · 2 of 15 papers
Recent preprints
Loading recent arXiv preprints…
Who publishes on it
Institutions on the most papers of this approach since 2023 (of 58 papers; from OpenAlex and the papers' affiliations).
- Tsinghua University · 5 papers
- Seoul National University · 2 papers
- Sun Yat-sen University · 2 papers
- The Chinese University of Hong Kong · 2 papers
- City University of Hong Kong · 2 papers
- Beihang University · 2 papers
- Nanyang Technological University · 2 papers
- Zhejiang University · 2 papers
- Peking University · 2 papers
- Xi’an Jiaotong University · 2 papers
Use it
Download BibTeX of 37 key papersOpen the topic in the interactive map
Get alerts. Describe your idea in scime atlas and save it (free scime account): you get a weekly email when new preprints land close to it.
Related approaches
Same keyword cluster
- Semi-supervised node representation learning (214 papers)
- Heterophily and imbalance on graphs (178 papers)
- LLMs and graph foundation models (117 papers)
- Multi-view graph clustering (70 papers)
Elsewhere in the topic
- Diffusion-based graph generation (138 papers)
- Graph anomaly detection (101 papers)
- Molecular graph pretraining (101 papers)
- Graph domain adaptation (82 papers)
- Graph contrastive learning analysis (61 papers)
- Graph out-of-distribution generalization (58 papers)
- Contrastive learning with negatives and views (51 papers)
- Augmentation-free graph learning (25 papers)
Benchmark numbers, ablations and baseline numbers are extracted by AI from each paper's full text and can be wrong; the paper is the authority. Data: results index of 2026-11-02, citation counts from OpenAlex (2026-10-09).