LGCVOct 23, 2021

Group-disentangled Representation Learning with Weakly-Supervised Regularization

arXiv:2110.12185v1
Originality Incremental advance
AI Analysis

This work addresses the problem of interpretable representation learning for AI researchers, offering an incremental improvement over existing weakly-supervised techniques.

The paper tackles the challenge of learning group-disentangled representations with weak supervision by proposing GroupVAE, a method using KL divergence regularization to enforce consistency, which significantly improves group disentanglement and enhances performance on downstream tasks like fair classification and 3D shape tasks.

Learning interpretable and human-controllable representations that uncover factors of variation in data remains an ongoing key challenge in representation learning. We investigate learning group-disentangled representations for groups of factors with weak supervision. Existing techniques to address this challenge merely constrain the approximate posterior by averaging over observations of a shared group. As a result, observations with a common set of variations are encoded to distinct latent representations, reducing their capacity to disentangle and generalize to downstream tasks. In contrast to previous works, we propose GroupVAE, a simple yet effective Kullback-Leibler (KL) divergence-based regularization across shared latent representations to enforce consistent and disentangled representations. We conduct a thorough evaluation and demonstrate that our GroupVAE significantly improves group disentanglement. Further, we demonstrate that learning group-disentangled representations improve upon downstream tasks, including fair classification and 3D shape-related tasks such as reconstruction, classification, and transfer learning, and is competitive to supervised methods.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes