# flyingdoog/awesome-graph-explainability-papers architecture

> Architecture diagram of the GitHub repository flyingdoog/awesome-graph-explainability-papers, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-06-16). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/flyingdoog/awesome-graph-explainability-papers
- Repository: https://github.com/flyingdoog/awesome-graph-explainability-papers

## Overview

1. This repository is a static curated bibliography, not an application or library. Its “product” is a maintained index of graph neural network explainability papers, with hyperlinks out to papers, code, surveys, and documentation.

2. The primary entry point is `README.md`. It acts as the landing page and main catalog, starting with a title and short scope statement, then listing papers grouped by category and year.

3. The content model is taxonomy-first. The README organizes the corpus into major sections such as Surveys, Platforms, and then year-based collections from 2026 back to “2020 and before.” This is the main navigation structure a reader would use.

4. The most important architectural boundary is between the repository and external sources. Almost every item links out to external paper hosts such as arXiv, OpenReview, ACM/IEEE/Springer pages, and occasionally project code repositories or platform documentation.

5. The “Platforms” section is a second subsystem distinct from the paper index. It highlights tooling and benchmark ecosystems around GNN explainability, including PyTorch Geometric explainability docs and external libraries/benchmarks like DIG, GraphXAI, GraphFramEx, GNNExplainer/PGExplainer code, and BAGEL.

6. The year sections function as a chronological changelog of the research field. They do not contain executable logic; instead they encode curation data and provenance for papers, enabling the repo to serve as a historical map of the area.

7. There is also a topic-oriented view implied by `bytopics.md`. Even though only the filename is visible here, it likely serves as an alternate index that reorganizes the same bibliography by method family, task type, or explanation style rather than by publication year.

8. Because the repository is documentation-only, there are no runtime services, build pipelines, databases, or APIs. The only “data flow” is manual curation: papers are added or reclassified in Markdown, and readers follow the embedded links to external sources.

9. The repository’s content boundary is broad but focused: it covers explainability for graph neural networks and closely related graph learning topics, but excludes implementation details except where a paper or platform is explicitly referenced.

10. For diagramming purposes, the repo should be modeled as a two-view knowledge base: a chronological bibliography (`README.md`) plus a topic index (`bytopics.md`), both backed by external scholarly sources and platform docs.

Main entry points: [`README.md`](https://github.com/flyingdoog/awesome-graph-explainability-papers/blob/main/README.md) (Platforms), [`bytopics.md`](https://github.com/flyingdoog/awesome-graph-explainability-papers/blob/main/bytopics.md) (By topics)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_repo["Repository views"]
  node_readme["README<br/>landing page<br/>[README.md]"]
  node_bytopics["By topics<br/>alternate index<br/>[bytopics.md]"]
  node_surveys["Surveys<br/>bibliography section<br/>[README.md]"]
  node_platforms["Platforms<br/>tooling section<br/>[README.md]"]
  node_timeline["Year index<br/>chronological bibliography<br/>[README.md]"]
  node_papers["Paper links<br/>scholarly references<br/>[README.md]"]
end

subgraph group_external["External sources"]
  node_arxiv(("arXiv<br/>paper host"))
  node_openreview(("OpenReview<br/>paper host"))
  node_publishers(("Publishers<br/>publication sites"))
  node_code(("Code repos<br/>project code"))
  node_docs(("Platform docs<br/>documentation"))
  node_pytorch_geometric(("PyG explain<br/>platform docs"))
  node_dig(("DIG<br/>explainability toolkit"))
  node_graphxai(("GraphXAI<br/>benchmarking platform"))
  node_graphframex(("GraphFramEx<br/>benchmark suite"))
  node_bagel(("BAGEL<br/>external platform"))
end

node_readme -->|"organizes"| node_surveys
node_readme -->|"includes"| node_platforms
node_readme -->|"orders by year"| node_timeline
node_readme -->|"lists"| node_papers
node_bytopics -->|"reindexes"| node_papers
node_surveys -.->|"links out"| node_arxiv
node_surveys -.->|"links out"| node_publishers
node_timeline -.->|"links out"| node_arxiv
node_timeline -.->|"links out"| node_openreview
node_timeline -.->|"links out"| node_publishers
node_papers -.->|"references"| node_code
node_platforms -.->|"points to"| node_docs
node_platforms -.->|"includes"| node_pytorch_geometric
node_platforms -.->|"includes"| node_dig
node_platforms -.->|"includes"| node_graphxai
node_platforms -.->|"includes"| node_graphframex
node_platforms -.->|"includes"| node_bagel
node_papers -.->|"occasionally links"| node_code

click node_readme "https://github.com/flyingdoog/awesome-graph-explainability-papers/blob/main/README.md"
click node_bytopics "https://github.com/flyingdoog/awesome-graph-explainability-papers/blob/main/bytopics.md"
click node_surveys "https://github.com/flyingdoog/awesome-graph-explainability-papers/blob/main/README.md"
click node_platforms "https://github.com/flyingdoog/awesome-graph-explainability-papers/blob/main/README.md"
click node_timeline "https://github.com/flyingdoog/awesome-graph-explainability-papers/blob/main/README.md"
click node_papers "https://github.com/flyingdoog/awesome-graph-explainability-papers/blob/main/README.md"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_readme,node_bytopics,node_surveys,node_platforms,node_timeline,node_papers toneBlue
class node_arxiv,node_openreview,node_publishers,node_code,node_docs,node_pytorch_geometric,node_dig,node_graphxai,node_graphframex,node_bagel toneAmber
```

## Components

### Repository views

Markdown entry points that curate and organize the bibliography.

- [README](https://github.com/flyingdoog/awesome-graph-explainability-papers/blob/main/README.md): landing page · Main bibliography entry point and curated catalog for graph neural network explainability papers. · `README.md`
- [By topics](https://github.com/flyingdoog/awesome-graph-explainability-papers/blob/main/bytopics.md): alternate index · Topic-oriented bibliography view that reorganizes the same corpus by method or explanation family. · `bytopics.md`
- [Surveys](https://github.com/flyingdoog/awesome-graph-explainability-papers/blob/main/README.md): bibliography section · Curated survey papers that summarize the field and define its subareas. · `README.md`
- [Platforms](https://github.com/flyingdoog/awesome-graph-explainability-papers/blob/main/README.md): tooling section · Explainability tooling, benchmarks, and ecosystem references around GNN explainability. · `README.md`
- [Year index](https://github.com/flyingdoog/awesome-graph-explainability-papers/blob/main/README.md): chronological bibliography · Year-based paper collections from 2026 back to 2020 and before, serving as the field timeline. · `README.md`
- [Paper links](https://github.com/flyingdoog/awesome-graph-explainability-papers/blob/main/README.md): scholarly references · Individual paper entries pointing to external publication pages and associated project pages. · `README.md`

### External sources

Out-of-repo paper hosts, code repositories, and platform documentation linked from the bibliography.

- **arXiv**: paper host · Primary preprint host linked by many bibliography entries.
- **OpenReview**: paper host · Peer-review and discussion pages for some papers.
- **Publishers**: publication sites · ACM, IEEE, Springer, and similar publisher pages linked from entries.
- **Code repos**: project code · External implementation repositories referenced by selected papers or platforms.
- **Platform docs**: documentation · External documentation for explainability frameworks and benchmarking platforms.
- **PyG explain**: platform docs · PyTorch Geometric explainability documentation referenced from the platforms section.
- **DIG**: explainability toolkit · External library ecosystem referenced as part of the platforms landscape.
- **GraphXAI**: benchmarking platform · External explainability benchmark or toolkit referenced in the platforms section.
- **GraphFramEx**: benchmark suite · External benchmark ecosystem for evaluating graph explanations.
- **BAGEL**: external platform · Another referenced explainability platform or benchmark ecosystem.

## Connections

- README → Surveys: organizes · README begins with a survey-oriented section.
- README → Platforms: includes · README contains a dedicated platforms and tooling section.
- README → Year index: orders by year · README presents the main bibliography as a chronological index.
- README → Paper links: lists · README enumerates individual paper entries as curated references.
- By topics → Paper links: reindexes · Topic view reorganizes the same paper corpus by theme.
- Surveys → arXiv: links out · Survey entries point to external preprint pages.
- Surveys → Publishers: links out · Survey entries may point to publisher pages.
- Year index → arXiv: links out · Chronological paper entries frequently point to arXiv.
- Year index → OpenReview: links out · Some entries point to OpenReview pages.
- Year index → Publishers: links out · Some entries point to ACM, IEEE, or Springer pages.
- Paper links → Code repos: references · Selected paper entries include project or implementation repositories.
- Platforms → Platform docs: points to · The platforms section highlights external documentation ecosystems.
- Platforms → PyG explain: includes · PyTorch Geometric explainability docs are part of the platforms boundary.
- Platforms → DIG: includes · DIG is cited as a related tooling ecosystem.
- Platforms → GraphXAI: includes · GraphXAI is cited as a benchmark or toolkit reference.
- Platforms → GraphFramEx: includes · GraphFramEx is cited as a benchmark or evaluation ecosystem.
- Platforms → BAGEL: includes · BAGEL is cited as part of the broader tooling landscape.
- Paper links → Code repos: occasionally links · Some paper entries point directly to code repositories.