Towards Learning Causal Representations from Multi-Instance Bags

• URL: http://arxiv.org/abs/2202.12570v1
• Date: Fri, 25 Feb 2022 09:13:00 GMT
• Title: Towards Learning Causal Representations from Multi-Instance Bags
• Authors: Weijia Zhang, Xuanhui Zhang, Hanwen Deng, Min-Ling Zhang
• Abstract summary: Multi-instance learning (MIL) is a type of weakly supervised learning that deals with objects represented as groups of instances. We propose the TargetedMIL algorithm, which learns semantically meaningful representations that can be interpreted as causal to the object of interest.
• Score: 38.68813959335736
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Although humans can easily identify the object of interest from groups of examples using group-level labels, most of the existing machine learning algorithms can only learn from individually labeled examples. Multi-instance learning (MIL) is a type of weakly supervised learning that deals with objects represented as groups of instances, and is theoretically capable of predicting instance labels from group-level supervision. Unfortunately, most existing MIL algorithms focus on improving the performances of group label predictions and cannot be used to accurately predict instance labels. In this work, we propose the TargetedMIL algorithm, which learns semantically meaningful representations that can be interpreted as causal to the object of interest. Utilizing the inferred representations, TargetedMIL excels at instance label predictions from group-level labels. Qualitative and quantitative evaluations on various datasets demonstrate the effectiveness of TargetedMIL.

Related papers

• Multi-Instance Partial-Label Learning with Margin Adjustment [52.05053599664198]
  Multi-instance partial-label learning (MIPL) is an emerging learning framework where each training sample is represented as a multi-instance bag associated with a candidate label set. Existing MIPL algorithms often overlook the margins for attention scores and predicted probabilities, leading to suboptimal generalization performance. We propose an algorithm named MIPLMA, which adjusts the margins for attention scores and predicted probabilities.
  arXiv  Detail & Related papers  (2025-01-22T02:47:17Z)
• ALVIN: Active Learning Via INterpolation [44.410677121415695]
  Active Learning Via INterpolation (ALVIN) conducts intra-class generalizations between examples from under-represented and well-represented groups. ALVIN identifies informative examples exposing the model to regions of the representation space that counteract the influence of shortcuts. Experimental results on six datasets encompassing sentiment analysis, natural language inference, and paraphrase detection demonstrate that ALVIN outperforms state-of-the-art active learning methods.
  arXiv  Detail & Related papers  (2024-10-11T16:44:39Z)
• Rethinking Multiple Instance Learning: Developing an Instance-Level Classifier via Weakly-Supervised Self-Training [14.16923025335549]
  Multiple instance learning (MIL) problem is currently solved from either bag-classification or instance-classification perspective. We formulate MIL as a semi-supervised instance classification problem, so that all the labeled and unlabeled instances can be fully utilized. We propose a weakly-supervised self-training method, in which we utilize the positive bag labels to construct a global constraint.
  arXiv  Detail & Related papers  (2024-08-09T01:53:41Z)
• Rethinking Multiple Instance Learning for Whole Slide Image Classification: A Good Instance Classifier is All You Need [18.832471712088353]
  We propose an instance-level weakly supervised contrastive learning algorithm for the first time under the MIL setting. We also propose an accurate pseudo label generation method through prototype learning.
  arXiv  Detail & Related papers  (2023-07-05T12:44:52Z)
• Disambiguated Attention Embedding for Multi-Instance Partial-Label Learning [68.56193228008466]
  In many real-world tasks, the concerned objects can be represented as a multi-instance bag associated with a candidate label set. Existing MIPL approach follows the instance-space paradigm by assigning augmented candidate label sets of bags to each instance and aggregating bag-level labels from instance-level labels. We propose an intuitive algorithm named DEMIPL, i.e., Disambiguated attention Embedding for Multi-Instance Partial-Label learning.
  arXiv  Detail & Related papers  (2023-05-26T13:25:17Z)
• Active Learning Principles for In-Context Learning with Large Language Models [65.09970281795769]
  This paper investigates how Active Learning algorithms can serve as effective demonstration selection methods for in-context learning. We show that in-context example selection through AL prioritizes high-quality examples that exhibit low uncertainty and bear similarity to the test examples.
  arXiv  Detail & Related papers  (2023-05-23T17:16:04Z)
• Multi-Instance Partial-Label Learning: Towards Exploiting Dual Inexact Supervision [53.530957567507365]
  In some real-world tasks, each training sample is associated with a candidate label set that contains one ground-truth label and some false positive labels. In this paper, we formalize such problems as multi-instance partial-label learning (MIPL) Existing multi-instance learning algorithms and partial-label learning algorithms are suboptimal for solving MIPL problems.
  arXiv  Detail & Related papers  (2022-12-18T03:28:51Z)
• Learning to Detect Instance-level Salient Objects Using Complementary Image Labels [55.049347205603304]
  We present the first weakly-supervised approach to the salient instance detection problem. We propose a novel weakly-supervised network with three branches: a Saliency Detection Branch leveraging class consistency information to locate candidate objects; a Boundary Detection Branch exploiting class discrepancy information to delineate object boundaries; and a Centroid Detection Branch using subitizing information to detect salient instance centroids.
  arXiv  Detail & Related papers  (2021-11-19T10:15:22Z)
• Active Learning in Incomplete Label Multiple Instance Multiple Label Learning [17.5720245903743]
  We propose a novel bag-class pair based approach for active learning in the MIML setting. Our approach is based on a discriminative graphical model with efficient and exact inference.
  arXiv  Detail & Related papers  (2021-07-22T17:01:28Z)

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

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.