paper-with-me

홈 › Papers

Discovering Concepts in Learned Representations using Statistical Inference and Interactive Visualization

2022-02-09 · Adrianna Janik, Kris Sankaran

Concept discovery is one of the open problems in the interpretability literature that is important for bridging the gap between non-deep learning experts and model end-users. Among current formulations, concepts defines them by as a direction in a learned representation space. This definition makes it possible to evaluate whether a particular concept significantly influences classification decisions for classes of interest. However, finding relevant concepts is tedious, as representation spaces are high-dimensional and hard to navigate. Current approaches include hand-crafting concept datasets and then converting them to latent space directions; alternatively, the process can be automated by clustering the latent space. In this study, we offer another two approaches to guide user discovery of meaningful concepts, one based on multiple hypothesis testing, and another on interactive visualization. We explore the potential value and limitations of these approaches through simulation experiments and an demo visual interface to real data. Overall, we find that these techniques offer a promising strategy for discovering relevant concepts in settings where users do not have predefined descriptions of them, but without completely automating the process.

📄 PDF Abstract BibTeX arXiv:2202.04753

Code (1)

adrijanik/concepts-exploration 공식 구현 pytorch

Tasks

Navigate

Similar Papers 제목 키워드 기반

Understanding Distributed Representations of Concepts in Deep Neural Networks without Supervision

2023-12-28 · Wonjoon Chang, Dahee Kwon, Jaesik Choi

Understanding intermediate representations of the concepts learned by deep learning classifiers is indispensable for interpreting general model behaviors. Existing approaches to reveal learned concepts often rely on huma…

Deep Learning

Discovering Interpretable Concepts in Large Generative Music Models

2025-05-18 · Nikhil Singh, Manuel Cherep, Pattie Maes

The fidelity with which neural networks can now generate content such as music presents a scientific opportunity: these systems appear to have learned implicit theories of the structure of such content through statistica…

ConceptLearner: Discovering Visual Concepts from Weakly Labeled Image Collections

2014-11-19 · CVPR 2015 6 · Bolei Zhou, Vignesh Jagadeesh, Robinson Piramuthu

Discovering visual knowledge from weakly labeled data is crucial to scale up computer vision recognition system, since it is expensive to obtain fully labeled data for a large number of concept categories. In this paper,…

object-detectionObject DetectionScene Recognition

Discovering Latent Concepts Learned in BERT

2022-05-15 · ICLR 2022 4 · Fahim Dalvi, Abdul Rafae Khan, Firoj Alam, Nadir Durrani 외

A large number of studies that analyze deep neural network models and their ability to encode various linguistic and non-linguistic concepts provide an interpretation of the inner mechanics of these models. The scope of …

Novel ConceptsPOS

HiMaCon: Discovering Hierarchical Manipulation Concepts from Unlabeled Multi-Modal Data

2025-10-13 · Ruizhe Liu, Pei Zhou, Qian Luo, Li Sun 외 arxiv

Effective generalization in robotic manipulation requires representations that capture invariant patterns of interaction across environments and tasks. We present a self-supervised framework for learning hierarchical man…

Representation Learning