On Learning Latent Models with Multi-Instance Weak Supervision
We consider a weakly supervised learning scenario where the supervision signal is generated by a transition function $\sigma$ of labels associated with multiple input instances. We formulate this problem as \emph{multi-instance Partial Label Learning (multi-instance PLL)}, which is an extension to the standard PLL problem. Our problem is met in different fields, including latent structural learning and neuro-symbolic integration. Despite the existence of many learning techniques, limited theoretical analysis has been dedicated to this problem. In this paper, we provide the first theoretical study of multi-instance PLL with possibly an unknown transition $\sigma$. Our main contributions are as follows. Firstly, we propose a necessary and sufficient condition for the learnability of the problem. This condition non-trivially generalizes and relaxes the existing small ambiguity degree in the PLL literature, since we allow the transition to be deterministic. Secondly, we derive Rademacher-style error bounds based on a top-$k$ surrogate loss that is widely used in the neuro-symbolic literature. Furthermore, we conclude with empirical experiments for learning under unknown transitions. The empirical results align with our theoretical findings; however, they also expose the issue of scalability in the weak supervision literature.
Code (0)
등록된 구현이 없습니다.
Tasks
Partial Label LearningWeakly-supervised LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Fully Convolutional Multi-Class Multiple Instance Learning
Multiple instance learning (MIL) can reduce the need for costly annotation in tasks such as semantic segmentation by weakening the required degree of supervision. We propose a novel MIL formulation of multi-class semanti…
Multiple Instance LearningSegmentationSemantic SegmentationWeakly-Supervised Semantic SegmentationSpatio-Temporal Instance Learning: Action Tubes from Class Supervision
The goal of this work is spatio-temporal action localization in videos, using only the supervision from video-level class labels. The state-of-the-art casts this weakly-supervised action localization regime as a Multiple…
Action LocalizationMultiple Instance LearningRerankingSpatio-Temporal Action Localization+2Weakly Supervised Disentanglement by Pairwise Similarities
Recently, researches related to unsupervised disentanglement learning with deep generative models have gained substantial popularity. However, without introducing supervision, there is no guarantee that the factors of in…
DisentanglementWISH: Weakly Supervised Instance Segmentation using Heterogeneous Labels
Instance segmentation traditionally relies on dense pixel-level annotations, making it costly and labor-intensive. To alleviate this burden, weakly supervised instance segmentation utilizes cost-effective weak labels…
Instance SegmentationSegmentationSemantic SegmentationWeakly-supervised instance segmentationMulti-Instance Causal Representation Learning for Instance Label Prediction and Out-of-Distribution Generalization
Multi-instance learning (MIL) deals with objects represented as bags of instances and can predict instance labels from bag-level supervision. However, significant performance gaps exist between instance-level MIL algorit…
Multiple Instance LearningOut-of-Distribution GeneralizationRepresentation Learning