paper-with-me

Papers

Analyzing Explainer Robustness via Probabilistic Lipschitzness of Prediction Functions

2022-06-24 · Zulqarnain Khan, Davin Hill, Aria Masoomi, Joshua Bone, Jennifer Dy

Machine learning methods have significantly improved in their predictive capabilities, but at the same time they are becoming more complex and less transparent. As a result, explainers are often relied on to provide interpretability to these black-box prediction models. As crucial diagnostics tools, it is important that these explainers themselves are robust. In this paper we focus on one particular aspect of robustness, namely that an explainer should give similar explanations for similar data inputs. We formalize this notion by introducing and defining explainer astuteness, analogous to astuteness of prediction functions. Our formalism allows us to connect explainer robustness to the predictor's probabilistic Lipschitzness, which captures the probability of local smoothness of a function. We provide lower bound guarantees on the astuteness of a variety of explainers (e.g., SHAP, RISE, CXPlain) given the Lipschitzness of the prediction function. These theoretical results imply that locally smooth prediction functions lend themselves to locally robust explanations. We evaluate these results empirically on simulated as well as real datasets.

📄 PDF Abstract BibTeX arXiv:2206.12481

Code (0)

등록된 구현이 없습니다.

Tasks

Prediction

Methods 이 논문이 사용한 방법론

SHAP 설명 없음

Similar Papers 제목 키워드 기반

Probabilistic Lipschitzness and the Stable Rank for Comparing Explanation Models

2024-02-29 · Lachlan Simpson, Kyle Millar, Adriel Cheng, Cheng-Chew Lim 외

Explainability models are now prevalent within machine learning to address the black-box nature of neural networks. The question now is which explainability model is most effective. Probabilistic Lipschitzness has demons…

PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networks

2020-10-12 · NeurIPS 2020 12 · Minh N. Vu, My T. Thai

In Graph Neural Networks (GNNs), the graph structure is incorporated into the learning of node representations. This complex structure makes explaining GNNs' predictions become much more challenging. In this paper, we pr…

Prediction

Graph Neural Networks for Vulnerability Detection: A Counterfactual Explanation

2024-04-24 · Zhaoyang Chu, Yao Wan, Qian Li, Yang Wu 외

Vulnerability detection is crucial for ensuring the security and reliability of software systems. Recently, Graph Neural Networks (GNNs) have emerged as a prominent code embedding approach for vulnerability detection, ow…

counterfactualCounterfactual ExplanationCounterfactual ReasoningVulnerability Detection

LaPLACE: Probabilistic Local Model-Agnostic Causal Explanations

2023-10-01 · Sein Minn

Machine learning models have undeniably achieved impressive performance across a range of applications. However, their often perceived black-box nature, and lack of transparency in decision-making, have raised concerns a…

Decision MakingFairnessmodelModel Selection

Verifying Relational Explanations: A Probabilistic Approach

2024-01-05 · Abisha Thapa Magar, Anup Shakya, Somdeb Sarkhel, Deepak Venugopal

Explanations on relational data are hard to verify since the explanation structures are more complex (e.g. graphs). To verify interpretable explanations (e.g. explanations of predictions made in images, text, etc.), typi…

counterfactual