LGFeb 22, 2021

Sign-regularized Multi-task Learning

arXiv:2102.11191v14 citations
Originality Incremental advance
AI Analysis

This work addresses a specific technical challenge in multi-task learning for improving generalization, but it appears incremental as it builds on existing methods by adding sign regularization.

The paper tackles the problem of distinguishing polarity and magnitude of feature weights in multi-task learning, proposing a new framework that regularizes feature weight signs across tasks and demonstrating its effectiveness through extensive experiments.

Multi-task learning is a framework that enforces different learning tasks to share their knowledge to improve their generalization performance. It is a hot and active domain that strives to handle several core issues; particularly, which tasks are correlated and similar, and how to share the knowledge among correlated tasks. Existing works usually do not distinguish the polarity and magnitude of feature weights and commonly rely on linear correlation, due to three major technical challenges in: 1) optimizing the models that regularize feature weight polarity, 2) deciding whether to regularize sign or magnitude, 3) identifying which tasks should share their sign and/or magnitude patterns. To address them, this paper proposes a new multi-task learning framework that can regularize feature weight signs across tasks. We innovatively formulate it as a biconvex inequality constrained optimization with slacks and propose a new efficient algorithm for the optimization with theoretical guarantees on generalization performance and convergence. Extensive experiments on multiple datasets demonstrate the proposed methods' effectiveness, efficiency, and reasonableness of the regularized feature weighted patterns.

Foundations

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

Your Notes