Related papers: Label-Free Explainability for Unsupervised Models

Label-Free Explainability for Unsupervised Models

URL: http://arxiv.org/abs/2203.01928v1
Date: Thu, 3 Mar 2022 18:59:03 GMT
Title: Label-Free Explainability for Unsupervised Models
Authors: Jonathan Crabb\'e and Mihaela van der Schaar
Abstract summary: Unsupervised black-box models are challenging to interpret. Most existing explainability methods require labels to select which component(s) of the black-box's output to interpret. We introduce two crucial extensions of post-hoc explanation techniques: (1) label-free feature importance and (2) label-free example importance.
Score: 95.94432031144716
License: http://creativecommons.org/licenses/by/4.0/
Abstract: Unsupervised black-box models are challenging to interpret. Indeed, most existing explainability methods require labels to select which component(s) of the black-box's output to interpret. In the absence of labels, black-box outputs often are representation vectors whose components do not correspond to any meaningful quantity. Hence, choosing which component(s) to interpret in a label-free unsupervised/self-supervised setting is an important, yet unsolved problem. To bridge this gap in the literature, we introduce two crucial extensions of post-hoc explanation techniques: (1) label-free feature importance and (2) label-free example importance that respectively highlight influential features and training examples for a black-box to construct representations at inference time. We demonstrate that our extensions can be successfully implemented as simple wrappers around many existing feature and example importance methods. We illustrate the utility of our label-free explainability paradigm through a qualitative and quantitative comparison of representation spaces learned by various autoencoders trained on distinct unsupervised tasks.

Related papers

Class-aware and Augmentation-free Contrastive Learning from Label Proportion [19.41511190742059]
Learning from Label Proportion (LLP) is a weakly supervised learning scenario in which training data is organized into predefined bags of instances. We propose an augmentation-free contrastive framework TabLLP-BDC that introduces class-aware supervision at the instance level. Our solution features a two-stage Bag Difference Contrastive (BDC) learning mechanism that establishes robust class-aware instance-level supervision.
arXiv Detail & Related papers (2024-08-13T09:04:47Z)
A Unified Label-Aware Contrastive Learning Framework for Few-Shot Named Entity Recognition [6.468625143772815]
We propose a unified label-aware token-level contrastive learning framework. Our approach enriches the context by utilizing label semantics as suffix prompts. It simultaneously optimize context-native and context-label contrastive learning objectives.
arXiv Detail & Related papers (2024-04-26T06:19:21Z)
Virtual Category Learning: A Semi-Supervised Learning Method for Dense Prediction with Extremely Limited Labels [63.16824565919966]
This paper proposes to use confusing samples proactively without label correction. A Virtual Category (VC) is assigned to each confusing sample in such a way that it can safely contribute to the model optimisation. Our intriguing findings highlight the usage of VC learning in dense vision tasks.
arXiv Detail & Related papers (2023-12-02T16:23:52Z)
Robust Representation Learning for Unreliable Partial Label Learning [86.909511808373]
Partial Label Learning (PLL) is a type of weakly supervised learning where each training instance is assigned a set of candidate labels, but only one label is the ground-truth. This is known as Unreliable Partial Label Learning (UPLL) that introduces an additional complexity due to the inherent unreliability and ambiguity of partial labels. We propose the Unreliability-Robust Representation Learning framework (URRL) that leverages unreliability-robust contrastive learning to help the model fortify against unreliable partial labels effectively.
arXiv Detail & Related papers (2023-08-31T13:37:28Z)
Imprecise Label Learning: A Unified Framework for Learning with Various Imprecise Label Configurations [91.67511167969934]
imprecise label learning (ILL) is a framework for the unification of learning with various imprecise label configurations. We demonstrate that ILL can seamlessly adapt to partial label learning, semi-supervised learning, noisy label learning, and, more importantly, a mixture of these settings.
arXiv Detail & Related papers (2023-05-22T04:50:28Z)
Bridging the Gap between Model Explanations in Partially Annotated Multi-label Classification [85.76130799062379]
We study how false negative labels affect the model's explanation. We propose to boost the attribution scores of the model trained with partial labels to make its explanation resemble that of the model trained with full labels.
arXiv Detail & Related papers (2023-04-04T14:00:59Z)
Contrastive Explanations for Model Interpretability [77.92370750072831]
We propose a methodology to produce contrastive explanations for classification models. Our method is based on projecting model representation to a latent space. Our findings shed light on the ability of label-contrastive explanations to provide a more accurate and finer-grained interpretability of a model's decision.
arXiv Detail & Related papers (2021-03-02T00:36:45Z)
An interpretable semi-supervised classifier using two different strategies for amended self-labeling [0.0]
Semi-supervised classification techniques combine labeled and unlabeled data during the learning phase. We present an interpretable self-labeling grey-box classifier that uses a black box to estimate the missing class labels and a white box to explain the final predictions.
arXiv Detail & Related papers (2020-01-26T19:37:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.