Learning Elastic Embeddings for Customizing On-Device Recommenders

TL;DR

This paper introduces RULE, a novel method for creating elastic embeddings that enable on-device recommenders to adapt to various memory constraints without retraining, improving efficiency and flexibility.

Contribution

The paper proposes a new elastic embedding approach and an automated search method for on-device recommenders, allowing flexible adaptation to different memory budgets without retraining.

Findings

RULE outperforms existing methods under tight memory constraints.

Elastic embeddings enable flexible on-device recommendation models.

The approach reduces the need for retraining when adapting to new memory budgets.

Abstract

In today's context, deploying data-driven services like recommendation on edge devices instead of cloud servers becomes increasingly attractive due to privacy and network latency concerns. A common practice in building compact on-device recommender systems is to compress their embeddings which are normally the cause of excessive parameterization. However, despite the vast variety of devices and their associated memory constraints, existing memory-efficient recommender systems are only specialized for a fixed memory budget in every design and training life cycle, where a new model has to be retrained to obtain the optimal performance while adapting to a smaller/larger memory budget. In this paper, we present a novel lightweight recommendation paradigm that allows a well-trained recommender to be customized for arbitrary device-specific memory constraints without retraining. The core idea is to compose elastic embeddings for each item, where an elastic embedding is the concatenation of a set of embedding blocks that are carefully chosen by an automated search function. Correspondingly, we propose an innovative approach, namely recommendation with universally learned elastic embeddings (RULE). To ensure the expressiveness of all candidate embedding blocks, RULE enforces a diversity-driven regularization when learning different embedding blocks. Then, a performance estimator-based evolutionary search function is designed, allowing for efficient specialization of elastic embeddings under any memory constraint for on-device recommendation. Extensive experiments on real-world datasets reveal the superior performance of RULE under tight memory budgets.