# Prototype-Aligned Federated Soft-Prompts for Continual Web Personalization

arXiv: https://arxiv.org/abs/2603.27678 · HTML: https://mlsanity.com/paper/2603.27678/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 45 references that are in the map.
- First posted on arXiv 29 Mar 2026.

## Builds on (most cited first, 20 of 20)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [Memory Aware Synapses: Learning what (not) to forget](https://mlsanity.com/paper/1711.09601/) (2017)
- [Ditto: Fair and Robust Federated Learning Through Personalization](https://mlsanity.com/paper/2012.04221/) (2020)
- [Large Language Models Empowered Personalized Web Agents](https://mlsanity.com/paper/2410.17236/) (2024)
- [Plan and Budget: Effective and Efficient Test-Time Scaling on Reasoning Large Language Models](https://mlsanity.com/paper/2505.16122/) (2025)
- [Ensuring User-side Fairness in Dynamic Recommender Systems](https://mlsanity.com/paper/2308.15651/) (2023)
- [Swift Sampler: Efficient Learning of Sampler by 10 Parameters](https://mlsanity.com/paper/2410.05578/) (2024)
- [Post-Training Attribute Unlearning in Recommender Systems](https://mlsanity.com/paper/2403.06737/) (2024)
- [Cognitive Personalized Search Integrating Large Language Models with an Efficient Memory Mechanism](https://mlsanity.com/paper/2402.10548/) (2024)
- [LENSLLM: Unveiling Fine-Tuning Dynamics for LLM Selection](https://mlsanity.com/paper/2505.03793/) (2025)
- [ReLoop: A Self-Correction Continual Learning Loop for Recommender Systems](https://mlsanity.com/paper/2204.11165/) (2022)
- [Structure Aware Incremental Learning with Personalized Imitation Weights for Recommender Systems](https://mlsanity.com/paper/2305.01204/) (2023)
- [Continual Transfer Learning for Cross-Domain Click-Through Rate Prediction at Taobao](https://mlsanity.com/paper/2208.05728/) (2022)
- [Real-Time Personalization for LLM-based Recommendation with Customized In-Context Learning](https://mlsanity.com/paper/2410.23136/) (2024)

## Built on by (most cited first, 5 of 5)

- [IMAGINE: Adaptive Schema-Imagery Enhanced Composition for Composed Video Retrieval](https://mlsanity.com/paper/2606.08144/) (2026)
- [MOSAIC: Orchestrating Collaborative Knowledge Tracing with Hierarchical Semantic Alignment](https://mlsanity.com/paper/2606.29049/) (2026)
- [Foundation-Assisted Active Learning for Object Detection Annotation](https://mlsanity.com/paper/2607.16671/) (2026)
- [AsyncCouple-Flow: Asynchronous Cross-Modal Coupling and Flow Matching for Spatio-Temporal Forecasting](https://mlsanity.com/paper/2609.16573/) (2026)
- [CoRe: Coherence and Relational Alignment for Multivariate Time Series Forecasting](https://mlsanity.com/paper/2609.19670/) (2026)

## Abstract (arXiv)

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.