AutoAssign+: Automatic Shared Embedding Assignment in Streaming Recommendation

TL;DR

AutoAssign+ is a reinforcement learning framework that improves streaming recommender systems by better initializing and managing ID embeddings, reducing memory use and addressing cold-start issues.

Contribution

It introduces a novel RL-based method for automatic shared embedding assignment, enhancing performance and memory efficiency in streaming recommenders.

Findings

Significantly improves recommendation accuracy.

Reduces memory consumption by 20-30%.

Effectively mitigates cold-start problems.

Abstract

In the domain of streaming recommender systems, conventional methods for addressing new user IDs or item IDs typically involve assigning initial ID embeddings randomly. However, this practice results in two practical challenges: (i) Items or users with limited interactive data may yield suboptimal prediction performance. (ii) Embedding new IDs or low-frequency IDs necessitates consistently expanding the embedding table, leading to unnecessary memory consumption. In light of these concerns, we introduce a reinforcement learning-driven framework, namely AutoAssign+, that facilitates Automatic Shared Embedding Assignment Plus. To be specific, AutoAssign+ utilizes an Identity Agent as an actor network, which plays a dual role: (i) Representing low-frequency IDs field-wise with a small set of shared embeddings to enhance the embedding initialization, and (ii) Dynamically determining which ID features should be retained or eliminated in the embedding table. The policy of the agent is optimized with the guidance of a critic network. To evaluate the effectiveness of our approach, we perform extensive experiments on three commonly used benchmark datasets. Our experiment results demonstrate that AutoAssign+ is capable of significantly enhancing recommendation performance by mitigating the cold-start problem. Furthermore, our framework yields a reduction in memory usage of approximately 20-30%, verifying its practical effectiveness and efficiency for streaming recommender systems.