paper-with-me

Papers

Pantypes: Diverse Representatives for Self-Explainable Models

2024-03-14 · Rune Kjærsgaard, Ahcène Boubekki, Line Clemmensen

Prototypical self-explainable classifiers have emerged to meet the growing demand for interpretable AI systems. These classifiers are designed to incorporate high transparency in their decisions by basing inference on similarity with learned prototypical objects. While these models are designed with diversity in mind, the learned prototypes often do not sufficiently represent all aspects of the input distribution, particularly those in low density regions. Such lack of sufficient data representation, known as representation bias, has been associated with various detrimental properties related to machine learning diversity and fairness. In light of this, we introduce pantypes, a new family of prototypical objects designed to capture the full diversity of the input distribution through a sparse set of objects. We show that pantypes can empower prototypical self-explainable models by occupying divergent regions of the latent space and thus fostering high diversity, interpretability and fairness.

📄 PDF Abstract BibTeX arXiv:2403.09383

Code (1)

runedk93/pantypes 공식 구현 pytorch

Tasks

DiversityExplainable ModelsFairness

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Towards Interpretable and Efficient Attention: Compressing All by Contracting a Few

2025-09-21 · Qishuai Wen, Zhiyuan Huang, Chun-Guang Li arxiv

Attention mechanisms have achieved significant empirical success in multiple fields, but their underlying optimization objectives remain unclear yet. Moreover, the quadratic complexity of self-attention has become increa…

Online Summarization via Submodular and Convex Optimization

2017-07-01 · CVPR 2017 7 · Ehsan Elhamifar, M. Clara De Paolis Kaluza

We consider the problem of subset selection in the online setting, where data arrive incrementally. Instead of storing and running subset selection on the entire dataset, we propose an incremental subset selection framew…

Video Summarization

Language Agents as Digital Representatives in Collective Decision-Making

2025-02-13 · Daniel Jarrett, Miruna Pîslar, Michiel A. Bakker, Michael Henry Tessler 외

Consider the process of collective decision-making, in which a group of individuals interactively select a preferred outcome from among a universe of alternatives. In this context, "representation" is the activity of mak…

Decision Making

ProtoVAE: A Trustworthy Self-Explainable Prototypical Variational Model

2022-10-15 · Srishti Gautam, Ahcene Boubekki, Stine Hansen, Suaiba Amina Salahuddin 외

The need for interpretable models has fostered the development of self-explainable classifiers. Prior approaches are either based on multi-stage optimization schemes, impacting the predictive performance of the model, or…

Diversitymodel

eX-ViT: A Novel eXplainable Vision Transformer for Weakly Supervised Semantic Segmentation

2022-07-12 · Lu Yu, Wei Xiang, Juan Fang, Yi-Ping Phoebe Chen 외

Recently vision transformer models have become prominent models for a range of vision tasks. These models, however, are usually opaque with weak feature interpretability. Moreover, there is no method currently built for …

AttributeSemantic SegmentationWeakly supervised Semantic SegmentationWeakly-Supervised Semantic Segmentation