Proceedings Article10.1145/2623330.2623759
Active learning for sparse bayesian multilabel classification
Deepak Vasisht,Andreas Damianou,Manik Varma,Ashish Kapoor +3 more
- 24 Aug 2014
- pp 472-481
TL;DR: This work proposes a novel inference algorithm for the sparse Bayesian multilabel model of [17] that enables a natural approximation of the mutual information objective and proves that the approximation leads to an identical solution to the exact optimization problem but at a fraction of the optimization cost.
read more
Abstract: We study the problem of active learning for multilabel classification We focus on the real-world scenario where the average number of positive (relevant) labels per data point is small leading to positive label sparsity Carrying out mutual information based near-optimal active learning in this setting is a challenging task since the computational complexity involved is exponential in the total number of labels We propose a novel inference algorithm for the sparse Bayesian multilabel model of [17] The benefit of this alternate inference scheme is that it enables a natural approximation of the mutual information objective We prove that the approximation leads to an identical solution to the exact optimization problem but at a fraction of the optimization cost This allows us to carry out efficient, non-myopic, and near-optimal active learning for sparse multilabel classification Extensive experiments reveal the effectiveness of the method
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Learning a Deep ConvNet for Multi-Label Classification With Partial Labels
Thibaut Durand,Nazanin Mehrasa,Greg Mori +2 more
- 01 Jun 2019
TL;DR: This article proposed to train a model with partial labels, i.e. only some labels are known per image, and empirically compare different labeling strategies to show the potential for using partial labels on multi-label datasets.
Exploring Representativeness and Informativeness for Active Learning
TL;DR: Wang et al. as discussed by the authors proposed a general active learning framework that effectively fuses the two active sampling criteria, namely representativeness and informativeness, without any assumption on data.
•Posted Content
The Emerging Trends of Multi-Label Learning
TL;DR: There has been a lack of systemic studies that focus explicitly on analyzing the emerging trends and new challenges of multi-label learning in the era of big data, and it is imperative to call for a comprehensive survey to fulfill this mission and delineate future research directions and new applications.
•Posted Content
Learning a Deep ConvNet for Multi-label Classification with Partial Labels
TL;DR: This work proposes to train a model with partial labels i.e. only some labels are known per image, and introduces a new classification loss that exploits the proportion of known labels per example.
152
ML-MG: Multi-label Learning with Missing Labels Using a Mixed Graph
Baoyuan Wu,Siwei Lyu,Bernard Ghanem +2 more
- 07 Dec 2015
TL;DR: This work proposes a unified model of label dependencies by constructing a mixed graph, which jointly incorporates (i) instance-level similarity and class co-occurrence as undirected edges and (ii) semantic label hierarchy as directed edges.
References
Active Learning Literature Survey
Burr Settles
- 01 Jan 2009
TL;DR: This report provides a general introduction to active learning and a survey of the literature, including a discussion of the scenarios in which queries can be formulated, and an overview of the query strategy frameworks proposed in the literature to date.
6.7K
Probabilistic Outputs for Support vector Machines and Comparisons to Regularized Likelihood Methods
John Platt
- 01 Jan 1999
TL;DR: The output of a lassi(cid:12)er should be a alibrated posterior probability to enable post-pro essing and a method to train a kernel lassi with a logit link and a regularized maximum likelihood is proposed.
6.1K
An analysis of approximations for maximizing submodular set functions--I
TL;DR: It is shown that a “greedy” heuristic always produces a solution whose value is at least 1 −[(K − 1/K]K times the optimal value, which can be achieved for eachK and has a limiting value of (e − 1)/e, where e is the base of the natural logarithm.
5.2K
•Posted Content
An analysis of approximations for maximizing submodular set functions II
Marshall L. Fisher,George L. Nemhauser,Laurence A. Wolsey +2 more
- 01 Jan 1978
TL;DR: In this article, the authors considered the problem of finding a maximum weight independent set in a matroid, where the elements of the matroid are colored and the items of the independent set can have no more than K colors.
3.5K
Bayesian Compressive Sensing
Shihao Ji,Ya Xue,Lawrence Carin +2 more
TL;DR: The underlying theory, an associated algorithm, example results, and comparisons to other compressive-sensing inversion algorithms in the literature are presented.
2.6K