Self-supervised self-supervision by combining deep learning and probabilistic logic

TL;DR

This paper introduces S4, a method that enhances deep probabilistic logic by automatically learning and proposing new self-supervision signals, significantly reducing human effort while maintaining high accuracy.

Contribution

S4 extends DPL by enabling automatic learning of self-supervision, reducing manual effort in crafting supervision signals, and improving model performance.

Findings

S4 can automatically generate accurate self-supervision signals.

S4 nearly matches supervised accuracy with minimal human input.

Experiments demonstrate effectiveness across multiple tasks.

Abstract

Labeling training examples at scale is a perennial challenge in machine learning. Self-supervision methods compensate for the lack of direct supervision by leveraging prior knowledge to automatically generate noisy labeled examples. Deep probabilistic logic (DPL) is a unifying framework for self-supervised learning that represents unknown labels as latent variables and incorporates diverse self-supervision using probabilistic logic to train a deep neural network end-to-end using variational EM. While DPL is successful at combining pre-specified self-supervision, manually crafting self-supervision to attain high accuracy may still be tedious and challenging. In this paper, we propose Self-Supervised Self-Supervision (S4), which adds to DPL the capability to learn new self-supervision automatically. Starting from an initial "seed," S4 iteratively uses the deep neural network to propose new self supervision. These are either added directly (a form of structured self-training) or verified by a human expert (as in feature-based active learning). Experiments show that S4 is able to automatically propose accurate self-supervision and can often nearly match the accuracy of supervised methods with a tiny fraction of the human effort.