Feature-Indexed Federated Recommendation with Residual-Quantized Codebooks

TL;DR

This work addresses the scalability and generalization limits of ID-indexed federated recommendations by introducing a feature-indexed communication paradigm that transmits codebooks instead of raw item embeddings. Built on Residual Quantization, the proposed RQFedRec framework realizes a collaborative-semantic dual-channel aggregation, guided by curriculum learning to emphasize semantic signals early and collaborative signals later. The approach achieves superior recommendation accuracy under constrained communication budgets, demonstrates robustness to noisy feedback, and offers enhanced privacy protections through codebook-based uploads and optional perturbations. Its practical impact lies in enabling privacy-preserving, scalable federated recommendations that generalize better across related items while reducing downstream communication costs.

Abstract

Federated recommendation provides a privacy-preserving solution for training recommender systems without centralizing user interactions. However, existing methods follow an ID-indexed communication paradigm that transmit whole item embeddings between clients and the server, which has three major limitations: 1) consumes uncontrollable communication resources, 2) the uploaded item information cannot generalize to related non-interacted items, and 3) is sensitive to client noisy feedback. To solve these problems, it is necessary to fundamentally change the existing ID-indexed communication paradigm. Therefore, we propose a feature-indexed communication paradigm that transmits feature code embeddings as codebooks rather than raw item embeddings. Building on this paradigm, we present RQFedRec, which assigns each item a list of discrete code IDs via Residual Quantization (RQ)-Kmeans. Each client generates and trains code embeddings as codebooks based on discrete code IDs provided by the server, and the server collects and aggregates these codebooks rather than item embeddings. This design makes communication controllable since the codebooks could cover all items, enabling updates to propagate across related items in same code ID. In addition, since code embedding represents many items, which is more robust to a single noisy item. To jointly capture semantic and collaborative information, RQFedRec further adopts a collaborative-semantic dual-channel aggregation with a curriculum strategy that emphasizes semantic codes early and gradually increases the contribution of collaborative codes over training. Extensive experiments on real-world datasets demonstrate that RQFedRec consistently outperforms state-of-the-art federated recommendation baselines while significantly reducing communication overhead.

Figures (4)

• Figure 1: Illustration of two communication paradigms in federated learning.
• Figure 2: The illustration of the RQFedRec framework. We only illustrate a single client for simplicity. The green part indicates collaborative information, the yellow part indicates semantic information, the red part indicates private information and the grey part indicates global information.
• Figure 3: The ablation study of our methods on Ml-100k dataset.
• Figure 4: The strength of collaborative information transmitted by different methods.

Theorems & Definitions (1)

• theorem 1