paper-with-me

홈 › Papers

Concept Learning in the Wild: Towards Algorithmic Understanding of Neural Networks

2024-12-15 · Elad Shohama, Hadar Cohena, Khalil Wattada, Havana Rikab, Dan Vilenchik

Explainable AI (XAI) methods typically focus on identifying essential input features or more abstract concepts for tasks like image or text classification. However, for algorithmic tasks like combinatorial optimization, these concepts may depend not only on the input but also on the current state of the network, like in the graph neural networks (GNN) case. This work studies concept learning for an existing GNN model trained to solve Boolean satisfiability (SAT). \textcolor{black}{Our analysis reveals that the model learns key concepts matching those guiding human-designed SAT heuristics, particularly the notion of 'support.' We demonstrate that these concepts are encoded in the top principal components (PCs) of the embedding's covariance matrix, allowing for unsupervised discovery. Using sparse PCA, we establish the minimality of these concepts and show their teachability through a simplified GNN. Two direct applications of our framework are (a) We improve the convergence time of the classical WalkSAT algorithm and (b) We use the discovered concepts to "reverse-engineer" the black-box GNN and rewrite it as a white-box textbook algorithm. Our results highlight the potential of concept learning in understanding and enhancing algorithmic neural networks for combinatorial optimization tasks.

📄 PDF Abstract BibTeX arXiv:2412.11205

Code (0)

등록된 구현이 없습니다.

Tasks

Combinatorial Optimizationtext-classificationText Classification

Methods 이 논문이 사용한 방법론

Focus 설명 없음
PCA Principle Components Analysis (PCA) is an unsupervised method primary used for dimensionality reduction within machine learning. PCA is calculated via a singular value…

Similar Papers 제목 키워드 기반

Fuck the Algorithm: Conceptual Issues in Algorithmic Bias

2025-05-16 · Catherine Stinson

Algorithmic bias has been the subject of much recent controversy. To clarify what is at stake and to make progress resolving the controversy, a better understanding of the concepts involved would be helpful. The discussi…

Recommendation Systems

MapInWild: A Remote Sensing Dataset to Address the Question What Makes Nature Wild

2022-12-05 · Burak Ekim, Timo T. Stomberg, Ribana Roscher, Michael Schmitt

Antrophonegic pressure (i.e. human influence) on the environment is one of the largest causes of the loss of biological diversity. Wilderness areas, in contrast, are home to undisturbed ecological processes. However, the…

Earth Observation

A Moral Framework for Understanding of Fair ML through Economic Models of Equality of Opportunity

2018-09-10 · Hoda Heidari, Michele Loi, Krishna P. Gummadi, Andreas Krause

We map the recently proposed notions of algorithmic fairness to economic models of Equality of opportunity (EOP)---an extensively studied ideal of fairness in political philosophy. We formally show that through our conce…

FairnessPhilosophy

Relevance-aware Algorithmic Recourse

2024-05-29 · Dongwhi Kim, Nuno Moniz

As machine learning continues to gain prominence, transparency and explainability are increasingly critical. Without an understanding of these models, they can replicate and worsen human bias, adversely affecting margina…

Fairness, Accuracy, and Unreliable Data

2024-08-28 · Kevin Stangl

This thesis investigates three areas targeted at improving the reliability of machine learning; fairness in machine learning, strategic classification, and algorithmic robustness. Each of these domains has special proper…

FairnessLearning Theory