pyg-team/pytorch_geometric

[Roadmap] Heterogeneous Graphs Explainability Support

Open

#9,112 创建于 2024年3月26日

在 GitHub 查看
 (11 评论) (0 反应) (1 负责人)Python (19,985 star) (3,514 fork)batch import
0 - Priority P0featuregood first issuehelp wantedroadmap

描述

🚀 The feature, motivation and pitch

Explainability is a key feature of GNNs, which is already implemented in PyG. However, of all the features introduced, only a few have been adapted to heterogeneous graphs.

Algorithms: Of all the algorithms implemented for explainability, only the Captum algorithm is compatible with heterogeneous graphs. It would be interesting to adapt other specific algorithms for graphs such as GNNExplainer or PGExplainer, and other algorithms such as AttentionExplainer.

Moreover, the algorithms adapted by PyG could be extended with new algorithms that have been published over the years (for example, see this survey), but this isn't just for heterogeneous graphs. Maybe in the future, we could work on creating new algorithms simultaneously for heterogeneous graphs, without this gap.

  • Adaptation of GNNExplainer for heterogeneous graphs.
  • Adaptation of PGExplainer for heterogeneous graphs.
  • Adaptation of AttentionExplainer for heterogeneous graphs.
  • Implementation of new explainability algorithms. System to allow adaptation to heterogeneous graphs without additional work.

Features: Some features available in the explanations of homogeneous GNNs are missing in heterogeneous GNNs. For example, the visualize_graph method of Explanation is not available for HeteroExplanation. This right now can be done with the get_explanation_subgraph method, and generating the plot by hand with NetworkX, but it would be nice to implement it to do it automatically.

  • Implementation of missing features for HeteroExplanation, such as visualize_graph.

Metrics: Currently, the available metrics such as Fidelity or Faithfulness are only available for homogeneous graphs, but those metrics could be adapted for heterogeneous graphs. To continue the work of #5628, we could think implementing new metrics for all kind of graphs, such as sparsity or stability (e.g. see https://arxiv.org/pdf/2012.15445.pdf)

  • Adaptation of fidelity, faithfulness and characterization score for heterogeneous graphs.
  • Sparsity metric for all graphs.
  • Stability metric for all graphs.

Alternatives

No response

Additional context

No response

贡献者指南

技术栈
python
领域
machine learning
议题类型
feature
难度面向新贡献者的预计实现难度，1 表示很小改动，5 表示专家级工作。
5
预计时间有经验贡献者完成调查、实现、测试并准备 pull request 的粗略时间范围。
over 1 week
活动状态议题当前的可参与程度：新鲜、活跃、陈旧、阻塞或等待维护者输入。
active
清晰度议题是否清楚说明期望改动、验收标准和下一步。
mostly clear
前置要求
PyTorch GeometricGraph Neural NetworksExplainability algorithmsPython
新手友好度1-100 的估计分数，表示该议题对首次贡献者的友好程度。
10
研究方向
Start by examining the existing homogeneous explainability implementations in PyG (e.g., GNNExplainer, PGExplainer) in the `torch geometric/explain/` directory. The next step is to adapt these algorithms to work with heterogeneous graphs, following the patterns used for CaptumExplainer. Additionally, implement missing features like `visualize graph` for `HeteroExplanation`. For metrics, extend Fidelity and Faithfulness for heterogeneous graphs and consider implementing sparsity and stability metrics as described in the linked paper.