paper-with-me

홈 › Papers

Promises and Pitfalls of Black-Box Concept Learning Models

2021-06-24 · Anita Mahinpei, Justin Clark, Isaac Lage, Finale Doshi-Velez, Weiwei Pan

Machine learning models that incorporate concept learning as an intermediate step in their decision making process can match the performance of black-box predictive models while retaining the ability to explain outcomes in human understandable terms. However, we demonstrate that the concept representations learned by these models encode information beyond the pre-defined concepts, and that natural mitigation strategies do not fully work, rendering the interpretation of the downstream prediction misleading. We describe the mechanism underlying the information leakage and suggest recourse for mitigating its effects.

📄 PDF Abstract BibTeX arXiv:2106.13314

Code (2)

mateoespinosa/concept-quality tf
tobias-opsahl/hybrid-concept-based-models pytorch

Tasks

Decision Making

Similar Papers 제목 키워드 기반

Promises and pitfalls of deep neural networks in neuroimaging-based psychiatric research

2023-01-20 · Fabian Eitel, Marc-André Schulz, Moritz Seiler, Henrik Walter 외

By promising more accurate diagnostics and individual treatment recommendations, deep neural networks and in particular convolutional neural networks have advanced to a powerful tool in medical imaging. Here, we first gi…

Transfer Learning

Natural Language Processing for Drug Discovery Knowledge Graphs: promises and pitfalls

2023-10-24 · J. Charles G. Jeynes, Tim James, Matthew Corney

Building and analysing knowledge graphs (KGs) to aid drug discovery is a topical area of research. A salient feature of KGs is their ability to combine many heterogeneous data sources in a format that facilitates discove…

Drug DiscoveryKnowledge Graphsnamed-entity-recognitionNamed Entity Recognition

Response to Promises and Pitfalls of Deep Kernel Learning

2025-09-25 · Andrew Gordon Wilson, Zhiting Hu, Ruslan Salakhutdinov, Eric P. Xing arxiv

This note responds to "Promises and Pitfalls of Deep Kernel Learning" (Ober et al., 2021). The marginal likelihood of a Gaussian process can be compartmentalized into a data fit term and a complexity penalty. Ober et al.…

Words as Bridges: Exploring Computational Support for Cross-Disciplinary Translation Work

2025-03-24 · Calvin Bao, Yow-Ting Shiue, Marine Carpuat, Joel Chan

Scholars often explore literature outside of their home community of study. This exploration process is frequently hampered by field-specific jargon. Past computational work often focuses on supporting translation work b…

TranslationWord Embeddings

A Survey on Graph Counterfactual Explanations: Definitions, Methods, Evaluation, and Research Challenges

2022-10-21 · Mario Alfonso Prado-Romero, Bardh Prenkaj, Giovanni Stilo, Fosca Giannotti

Graph Neural Networks (GNNs) perform well in community detection and molecule classification. Counterfactual Explanations (CE) provide counter-examples to overcome the transparency limitations of black-box models. Due to…

BenchmarkingCommunity DetectioncounterfactualCounterfactual Explanation+3