原型对齐的联邦软提示用于持续网页个性化
Prototype-Aligned Federated Soft-Prompts for Continual Web Personalization
AI总结：
本文提出ProtoFed-SP框架，通过双时间尺度软提示实现隐私保护的持续个性化，提升NDCG和HR指标，降低遗忘率并保持准确性。
摘要：
持续网页个性化对于用户参与至关重要，但现实中的非平稳性和隐私约束使快速适应而不忘长时偏好变得困难。本文通过寻求一个隐私意识强、参数高效的接口来填补这一空白，该接口在用户/会话层面控制稳定性与可塑性，并将用户记忆与共享语义先验联系起来。我们提出ProtoFed-SP，一种基于提示的框架，将双时间尺度的软提示注入冻结的骨干网络：一个快速、稀疏的短期提示跟踪会话意图，而一个缓慢的长期提示则锚定在一个小的服务器端原型库中，通过差分隐私联邦聚合持续更新。查询被路由到Top-M原型以组成个性化提示。在八个基准测试中，ProtoFed-SP在NDCG@10上比最强基线提高+2.9%，在HR@10上提高+2.0%，在Amazon-Books、H&M和Taobao上分别达到+5.0%、+2.5%和+2.2%的提升。它还降低了遗忘率（AF）和步骤到95%，并在实际DP预算下保持准确性。我们的贡献是提供一个统一的、隐私意识的提示接口，通过原型锚定实现稳健的持续个性化，并提供透明、可控的机制来平衡部署中的稳定性与可塑性。
英文摘要：
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 contribution is a unifying, privacy-aware prompting interface with prototype anchoring that delivers robust continual personalization and offers a transparent, controllable mechanism to balance stability and plasticity in deployment.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
