# thunlp/GNNPapers

Must-read papers on graph neural networks (GNN)

Repository: https://github.com/thunlp/GNNPapers
Canonical: https://ross.abutalabs.com/products/gnnpapers
License Family: other
Topics: paper-list, gnn
Last push: 2023-12-20T03:33:14+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2810, "days_push": 987, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 16829, forks 3008 (observed 2026-08-28T04:11:17.339808+00:00)

## What it is
A curated reading list of must-read papers on graph neural networks (GNN), organized into surveys, models, and application areas. It is maintained by researchers from Tsinghua University's THUNLP group.

## Use cases
- find must-read papers on graph neural networks
- get started learning GNNs
- find GNN survey papers
- discover GNN applications in chemistry, recommendation, and NLP
- build a reading plan for graph deep learning research
- find papers on graph pooling and explainability

## When to choose
- you want a curated, categorized bibliography of GNN literature
- you are a student or researcher entering the graph neural network field
- you need pointers to surveys and foundational GNN models

## When to avoid
- you need GNN code or a software library rather than papers
- you need up-to-date coverage of the newest GNN research, as updates have slowed
- you want tutorials with hands-on exercises instead of a paper list

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: documentation
- domain: machine-learning, deep-learning, tutorials, awesome-lists
- platform: cross-platform
- tags: graph-neural-networks, gnn, paper-list, reading-list, research

## Member repositories
- thunlp/GNNPapers (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:17.339808+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:03:49.217640+00:00, confidence not recorded.
  - readme: https://github.com/thunlp/GNNPapers (fetched 2026-08-28T04:11:17.339808+00:00, sha dbbc47d441d1)
- Data as of 2026-08-30T08:39:29.467469+00:00.