Skip to content

Document PyG graph model attribution workflow - #1862

Open
craymichael wants to merge 1 commit into
meta-pytorch:masterfrom
craymichael:docs/246-pyg-graph-model-faq
Open

craymichael wants to merge 1 commit into
meta-pytorch:masterfrom
craymichael:docs/246-pyg-graph-model-faq

Conversation

@craymichael

Copy link
Copy Markdown
Contributor

Fixes #246.

Summary

  • Adds an FAQ entry for using Captum with PyTorch Geometric and graph neural network models.
  • Points users to PyG's graph-native Captum integration: CaptumExplainer, to_captum_model, and to_captum_input.
  • Shows the lower-level direct Captum pattern for attributing node features while passing edge_index / batch as additional_forward_args.
  • Clarifies that edge_index is an integer topology tensor and should not be attributed directly; edge or topology importance should use an edge mask, edge weight, or edge feature tensor representation.

Test Plan

  • git diff --check
  • Documentation-only change; no runtime tests run.
Fixes meta-pytorch#246.

Issue: meta-pytorch#246

Issue summary: Users asked how to use Captum with PyTorch Geometric / graph neural network models and whether Captum needs graph-native support.

Summary:

- Adds an FAQ entry for PyTorch Geometric and graph neural network attribution workflows.

- Points users to PyG's CaptumExplainer, to_captum_model, and to_captum_input utilities for graph-native node / edge masks.

- Shows the lower-level Captum pattern for tensor node-feature attribution with graph structure passed as additional_forward_args.

Test Plan:

- git diff --check

- Documentation-only change; no runtime tests run.

This branch has not been deployed

No deployments
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

1 participant