Contrasting quadratic assignments for set-based representation learning
The standard approach to contrastive learning is to maximize the agreement between different views of the data. The views are ordered in pairs, such that they are either positive, encoding different views of the same object, or negative, corresponding to views of different objects. The supervisory signal comes from maximizing the total similarity over positive pairs, while the negative pairs are needed to avoid collapse. In this work, we note that the approach of considering individual pairs cannot account for both intra-set and inter-set similarities when the sets are formed from the views of the data. It thus limits the information content of the supervisory signal available to train representations. We propose to go beyond contrasting individual pairs of objects by focusing on contrasting objects as sets. For this, we use combinatorial quadratic assignment theory designed to evaluate set and graph similarities and derive set-contrastive objective as a regularizer for contrastive learning methods. We conduct experiments and demonstrate that our method improves learned representations for the tasks of metric learning and self-supervised classification.
Code (1)
Tasks
Contrastive LearningMetric LearningRepresentation LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Graph Representation Learning via Contrasting Cluster Assignments
With the rise of contrastive learning, unsupervised graph representation learning has been booming recently, even surpassing the supervised counterparts in some machine learning tasks. Most of existing contrastive models…
ClusteringContrastive LearningGraph Representation LearningRepresentation LearningDeep Multiview Clustering by Contrasting Cluster Assignments
Multiview clustering (MVC) aims to reveal the underlying structure of multiview data by categorizing data samples into clusters. Deep learning-based methods exhibit strong feature learning capabilities on large-scale dat…
ClusteringContrastive LearningMultiview ClusteringSelf-supervised Video Representation Learning with Cross-Stream Prototypical Contrasting
Instance-level contrastive learning techniques, which rely on data augmentation and a contrastive loss function, have found great success in the domain of visual representation learning. They are not suitable for exploit…
Action RecognitionAction Recognition In VideosContrastive LearningData Augmentation+9Soft Contrastive Learning for Time Series
Contrastive learning has shown to be effective to learn representations from time series in a self-supervised way. However, contrasting similar time series instances or values from adjacent timestamps within a time serie…
Anomaly DetectionContrastive LearningTime SeriesTransfer LearningUnsupervised Learning of Visual Features by Contrasting Cluster Assignments
Unsupervised image representations have significantly reduced the gap with supervised pretraining, notably with the recent achievements of contrastive learning methods. These contrastive methods typically work online and…
Contrastive LearningData AugmentationImage ClassificationSelf-Supervised Image Classification+1