Learning Weakly-Supervised Contrastive Representations

02/14/2022
by   Yao-Hung Hubert Tsai, et al.
16

We argue that a form of the valuable information provided by the auxiliary information is its implied data clustering information. For instance, considering hashtags as auxiliary information, we can hypothesize that an Instagram image will be semantically more similar with the same hashtags. With this intuition, we present a two-stage weakly-supervised contrastive learning approach. The first stage is to cluster data according to its auxiliary information. The second stage is to learn similar representations within the same cluster and dissimilar representations for data from different clusters. Our empirical experiments suggest the following three contributions. First, compared to conventional self-supervised representations, the auxiliary-information-infused representations bring the performance closer to the supervised representations, which use direct downstream labels as supervision signals. Second, our approach performs the best in most cases, when comparing our approach with other baseline representation learning methods that also leverage auxiliary data information. Third, we show that our approach also works well with unsupervised constructed clusters (e.g., no auxiliary information), resulting in a strong unsupervised representation learning approach.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/05/2021

Integrating Auxiliary Information in Self-supervised Learning

This paper presents to integrate the auxiliary information (e.g., additi...
research
03/15/2022

Improving Event Representation via Simultaneous Weakly Supervised Contrastive Learning and Clustering

Representations of events described in text are important for various ta...
research
12/31/2021

Representation Learning via Consistent Assignment of Views to Clusters

We introduce Consistent Assignment for Representation Learning (CARL), a...
research
10/16/2021

Seeking Patterns, Not just Memorizing Procedures: Contrastive Learning for Solving Math Word Problems

Math Word Problem (MWP) solving needs to discover the quantitative relat...
research
12/14/2020

Odd-One-Out Representation Learning

The effective application of representation learning to real-world probl...
research
04/19/2021

Self-supervised Representation Learning With Path Integral Clustering For Speaker Diarization

Automatic speaker diarization techniques typically involve a two-stage p...
research
03/31/2023

Weakly-Supervised Text-driven Contrastive Learning for Facial Behavior Understanding

Contrastive learning has shown promising potential for learning robust r...

Please sign up or login with your details

Forgot password? Click here to reset