AutoLoss: Automated Loss Function Search in Recommendations

by   Xiangyu Zhao, et al.

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.


page 1

page 2

page 3

page 4


AM-LFS: AutoML for Loss Function Search

Designing an effective loss function plays an important role in visual a...

AutoField: Automating Feature Selection in Deep Recommender Systems

Feature quality has an impactful effect on recommendation performance. T...

CROLoss: Towards a Customizable Loss for Retrieval Models in Recommender Systems

In large-scale recommender systems, retrieving top N relevant candidates...

Determinantal Point Process Likelihoods for Sequential Recommendation

Sequential recommendation is a popular task in academic research and clo...

User behavior understanding in real world settings

How to extract meaningful information in user historical behavior plays ...

Path-Based Reasoning over Heterogeneous Networks for Recommendation via Bidirectional Modeling

Heterogeneous Information Network (HIN) is a natural and general represe...

Please sign up or login with your details

Forgot password? Click here to reset