Theoretical Analysis of Submodular Information Measures for Targeted Data Subset Selection
Not on the map. Why?
Abstract (arXiv)
With increasing volume of data being used across machine learning tasks, the capability to target specific subsets of data becomes more important. To aid in this capability, the recently proposed Submodular Mutual Information (SMI) has been effectively applied across numerous tasks in literature to perform targeted subset selection with the aid of a exemplar query set. However, all such works are deficient in providing theoretical guarantees for SMI in terms of its sensitivity to a subset's relevance and coverage of the targeted data. For the first time, we provide such guarantees by deriving similarity-based bounds on quantities related to relevance and coverage of the targeted data. With these bounds, we show that the SMI functions, which have empirically shown success in multiple applications, are theoretically sound in achieving good query relevance and query coverage.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 13 of its 17 references that are in the map. First posted on arXiv 21 Feb 2024.
Builds on
13 of 17 references.
References · 13
- 2020Submodular Combinatorial Information Measures with Applications in Machine Learningcited by 88
- 2021SIMILAR: Submodular Information Measures Based Active Learning In Realistic Scenarioscited by 84
- 2021PRISM: A Rich Class of Parameterized Submodular Information Measures for Guided Subset Selectioncited by 51
- 2022Submodularity In Machine Learning and Artificial Intelligencecited by 38
- 2021TALISMAN: Targeted Active Learning for Object Detection with Rare Classes and Slices using Submodular Mutual Informationcited by 27
- 2022CLINICAL: Targeted Active Learning for Imbalanced Medical Image Classificationcited by 9
- 2019A Memoization Framework for Scaling Submodular Optimization to Large Scale Problemscited by 8
- 2022Active Data Discovery: Mining Unknown Data using Submodular Information Measurescited by 6
- 2021DITTO: Data-efficient and Fair Targeted Subset Selection for ASR Accent Adaptationcited by 5
- 2023Beyond Active Learning: Leveraging the Full Potential of Human Interaction via Auto-Labeling, Human Correction, and Human Verificationcited by 4
- 2022PLATINUM: Semi-Supervised Model Agnostic Meta-Learning using Submodular Mutual Informationcited by 3
- 2023STREAMLINE: Streaming Active Learning for Realistic Multi-Distributional Settingscited by 2
Built on by
Citing papers per year: 2026: 1.
1 paper.