用可私密更新的原型锚定提示，实现用户持续个性化推荐。
Prototype-Aligned Federated Soft-Prompts for Continual Web Personalization
- 双时标软提示注入：快短时跟踪会话意图，慢长时绑定服务器原型库。
- 在8个基准上提升NDCG@10达2.9%，亚马逊图书数据集提升5.0%。
- 支持差分隐私联邦聚合，适合注重隐私与长期记忆的在线推荐系统。
持续性网页个性化对用户参与度至关重要，但现实中的非平稳性和隐私限制使得快速适应且不遗忘长期偏好十分困难。为此，我们提出一种兼顾隐私与参数效率的接口，从用户/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关联。我们设计了ProtoFed-SP，一种基于提示的框架，在冻结主干网络中注入双时标软提示：快速稀疏的短期提示追踪会话意图，缓慢更新的长期提示锚定于一个小型服务器端原型库，通过差分隐私联邦聚合持续刷新。查询通过匹配前M个原型来组合个性化提示。在八个基准测试中，ProtoFed-SP相比最强基线将NDCG@10提升2.9%，HR@10提升2.0%；在Amazon-Books上相较INFER提升5.0%（NDCG），H&M上相较Dual-LoRA提升2.5%，Taobao上相较FedRAP提升2.2%。同时降低遗忘率（AF）和达到95%准确率所需步数，在实际差分隐私预算下仍保持精度。贡献在于提供一种统一、隐私友好的提示接口，通过原型锚定实现鲁棒的持续个性化，并为部署中的稳定性与可塑性平衡提供透明可控机制。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。