Feature Attribution in Directed Acyclic Graphs Using Edge Intervention
Quick Answer
DAG-SHAP introduces a novel feature attribution method for directed acyclic graphs, addressing limitations of existing Shapley value-based methods by treating feature edges as individual attribution objects.
Quick Take
DAG-SHAP introduces a novel feature attribution method for directed acyclic graphs, addressing limitations of existing Shapley value-based methods by treating feature edges as individual attribution objects. This approach captures both externality and exogenous contributions effectively, validated through extensive experiments on real and synthetic datasets.
Key Points
- DAG-SHAP improves feature attribution by focusing on edges rather than nodes.
- The method captures both externality and exogenous influences of features.
- Extensive experiments confirm the effectiveness of DAG-SHAP on various datasets.
- An efficient approximation method for computing DAG-SHAP is introduced.
- Code for DAG-SHAP is available on GitHub.
Paper Resources
Article Excerpt
From source RSS / original summaryarXiv:2606. 15273v1 Announce Type: new Abstract: Shapley value-based feature attribution methods face challenges in scenarios involving complex feature interactions and causal relationships, even when a causal structure is provided. Existing methods typically adopt a node-centric view, attributing importance solely to individual features. Consequently, they often fail to simultaneously capture the externality and exogenous influence of features, leading to unreasonable interpretations.
To overcome these limitations, we propose a novel feature attribution method called DAG-SHAP, which is based on edge intervention. DAG-SHAP treats each feature edge as an individual attribution object, ensuring that both externality and exogenous contributions of features are appropriately captured. Additionally, we introduce an approximation method for efficiently computing DAG-SHAP. Extensive experiments on both real and synthetic datasets validate the effectiveness of DAG-SHAP.
Our code is available at https://github. com/ZJU-DIVER/DAG-SHAP.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →Arbor: Tree Search as a Cognition Layer for Autonomous Agents
Arbor introduces a multi-agent framework utilizing structured tree search for optimizing LLM inference, achieving up to 193% throughput-latency improvement compared to vendor-optimized systems. It employs an Orchestrator and Critic agent for stability and coordination, demonstrating hardware-agnostic performance with minimal variance.