Weakly Supervised Label Learning Flows

TL;DR

This paper introduces Label Learning Flows (LLF), a generative normalizing flow-based framework for weakly supervised learning that models label distributions conditioned on weak signals, outperforming existing methods.

Contribution

The paper proposes a novel generative framework using normalizing flows for weakly supervised label learning, avoiding explicit label estimation and enabling sampling-based predictions.

Findings

LLF outperforms baseline methods in experiments.

The approach effectively models label distributions conditioned on weak signals.

Training avoids explicit label estimation, simplifying the learning process.

Abstract

Supervised learning usually requires a large amount of labelled data. However, attaining ground-truth labels is costly for many tasks. Alternatively, weakly supervised methods learn with cheap weak signals that only approximately label some data. Many existing weakly supervised learning methods learn a deterministic function that estimates labels given the input data and weak signals. In this paper, we develop label learning flows (LLF), a general framework for weakly supervised learning problems. Our method is a generative model based on normalizing flows. The main idea of LLF is to optimize the conditional likelihoods of all possible labelings of the data within a constrained space defined by weak signals. We develop a training method for LLF that trains the conditional flow inversely and avoids estimating the labels. Once a model is trained, we can make predictions with a sampling algorithm. We apply LLF to three weakly supervised learning problems. Experiment results show that our method outperforms many baselines we compare against.