Year: 2021
Type: preprint
Abstract: Designing an effective loss function plays a crucial role in training deep recommender systems. Most existing works often leverage a predefined and fixed loss function that could lead to suboptimal recommendation quality and training efficiency. Some recent efforts rely on exhaustively or manually searched weights to fuse a group of candidate loss functions, which is exceptionally costly in computation and time. They also neglect the various convergence behaviors of different data examples. In this work, we propose an AutoLoss framework that can automatically and adaptively search for the appropriate loss function from a set of candidates. To be specific, we develop a novel controller network, which can dynamically adjust the loss probabilities in a differentiable manner. Unlike existing algorithms, the proposed controller can adaptively generate the loss probabilities for different data examples according to their varied convergence behaviors. Such design improves the model's generalizability and transferability between deep recommender systems and datasets. We evaluate the proposed framework on two benchmark datasets. The results show that AutoLoss outperforms representative baselines. Further experiments have been conducted to deepen our understandings of AutoLoss, including its transferability, components and training efficiency.
Source: arXiv (Cornell University)
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funder: National Science Foundation
Awards: III: Small: Collaborative Research: Effective Labeled Data Generation via Generative Adversarial Learning, CAREER: Real-World Networks: Modeling and Analysis of Signed Networks with Positive and Negative Links, SaTC: CORE: Small: Side-channel Attacks Against Mobile Users: Singularity Detection, Behavior Identification, and Automated Rectification, FW-HTF-RM: Intelligent Social Network Interventions to Augment Human Cognition for Interdisciplinary Interactions in Project Teams, III: Small: Unsupervised Feature Selection in the Era of Big Data, III: Small: Collaborative Research: A General Feature Learning Framework for Dynamic Attributed Networks
OpenAlex ID: W3167583601