Self-Supervised Relational Reasoning for Representation Learning

by   Massimiliano Patacchiola, et al.

In self-supervised learning, a system is tasked with achieving a surrogate objective by defining alternative targets on a set of unlabeled data. The aim is to build useful representations that can be used in downstream tasks, without costly manual annotation. In this work, we propose a novel self-supervised formulation of relational reasoning that allows a learner to bootstrap a signal from information implicit in unlabeled data. Training a relation head to discriminate how entities relate to themselves (intra-reasoning) and other entities (inter-reasoning), results in rich and descriptive representations in the underlying neural network backbone, which can be used in downstream tasks such as classification and image retrieval. We evaluate the proposed method following a rigorous experimental procedure, using standard datasets, protocols, and backbones. Self-supervised relational reasoning outperforms the best competitor in all conditions by an average 14 in accuracy, and the most recent state-of-the-art model by 3 effectiveness of the method to the maximization of a Bernoulli log-likelihood, which can be considered as a proxy for maximizing the mutual information, resulting in a more efficient objective with respect to the commonly used contrastive losses.


page 4

page 17

page 18

page 19

page 21

page 22


Self-Supervised Time Series Representation Learning by Inter-Intra Relational Reasoning

Self-supervised learning achieves superior performance in many domains b...

Conditional Contrastive Learning: Removing Undesirable Information in Self-Supervised Representations

Self-supervised learning is a form of unsupervised learning that leverag...

Improving Visual Reasoning by Exploiting The Knowledge in Texts

This paper presents a new framework for training image-based classifiers...

Vector-Quantized Autoregressive Predictive Coding

Autoregressive Predictive Coding (APC), as a self-supervised objective, ...

Understanding the World Through Action

The recent history of machine learning research has taught us that machi...

Self-supervised Representation Learning with Relative Predictive Coding

This paper introduces Relative Predictive Coding (RPC), a new contrastiv...

Concurrent Discrimination and Alignment for Self-Supervised Feature Learning

Existing self-supervised learning methods learn representation by means ...

Code Repositories


Official PyTorch implementation of the paper "Self-Supervised Relational Reasoning for Representation Learning", NeurIPS 2020 Spotlight.

view repo