GraphHash: Graph Clustering Enables Parameter Efficiency in Recommender Systems

TL;DR

GraphHash introduces a graph-based clustering method for recommender systems that significantly reduces embedding table sizes while improving retrieval and prediction performance, leveraging collaborative signals.

Contribution

It is the first to apply modularity-based bipartite graph clustering for embedding reduction, connecting graph theory with message-passing in recommender systems.

Findings

Achieves over 101% improvement in recall with 75% smaller embedding tables.

Outperforms traditional hashing baselines on retrieval and CTR tasks.

Provides a computationally efficient, graph-based alternative to ID hashing.

Abstract

Deep recommender systems rely heavily on large embedding tables to handle high-cardinality categorical features such as user/item identifiers, and face significant memory constraints at scale. To tackle this challenge, hashing techniques are often employed to map multiple entities to the same embedding and thus reduce the size of the embedding tables. Concurrently, graph-based collaborative signals have emerged as powerful tools in recommender systems, yet their potential for optimizing embedding table reduction remains unexplored. This paper introduces GraphHash, the first graph-based approach that leverages modularity-based bipartite graph clustering on user-item interaction graphs to reduce embedding table sizes. We demonstrate that the modularity objective has a theoretical connection to message-passing, which provides a foundation for our method. By employing fast clustering algorithms, GraphHash serves as a computationally efficient proxy for message-passing during preprocessing and a plug-and-play graph-based alternative to traditional ID hashing. Extensive experiments show that GraphHash substantially outperforms diverse hashing baselines on both retrieval and click-through-rate prediction tasks. In particular, GraphHash achieves on average a 101.52% improvement in recall when reducing the embedding table size by more than 75%, highlighting the value of graph-based collaborative information for model reduction. Our code is available at https://github.com/snap-research/GraphHash.