[2603.27678] Prototype-Aligned Federated Soft-Prompts for Continual Web Personalization

Computer Science > Machine Learning arXiv:2603.27678 (cs) [Submitted on 29 Mar 2026] Title:Prototype-Aligned Federated Soft-Prompts for Continual Web Personalization Authors:Canran Xiao, Liwei Hou View a PDF of the paper titled Prototype-Aligned Federated Soft-Prompts for Continual Web Personalization, by Canran Xiao and Liwei Hou View PDF HTML (experimental) Abstract:Continual web personalization is essential for engagement, yet real-world non-stationarity and privacy constraints make it hard to adapt quickly without forgetting long-term preferences. We target this gap by seeking a privacy-conscious, parameter-efficient interface that controls stability-plasticity at the user/session level while tying user memory to a shared semantic prior. We propose ProtoFed-SP, a prompt-based framework that injects dual-timescale soft prompts into a frozen backbone: a fast, sparse short-term prompt tracks session intent, while a slow long-term prompt is anchored to a small server-side prototype library that is continually refreshed via differentially private federated aggregation. Queries are routed to Top-M prototypes to compose a personalized prompt. Across eight benchmarks, ProtoFed-SP improves NDCG@10 by +2.9% and HR@10 by +2.0% over the strongest baselines, with notable gains on Amazon-Books (+5.0% NDCG vs. INFER), H&M (+2.5% vs. Dual-LoRA), and Taobao (+2.2% vs. FedRAP). It also lowers forgetting (AF) and Steps-to-95% and preserves accuracy under practical DP budgets. Our contrib...