# MDiffFR: Modality-Guided Diffusion Generation for Cold-start Items in Federated Recommendation

arXiv: https://arxiv.org/abs/2512.24715 · HTML: https://mlsanity.com/paper/2512.24715/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Diffusion recommenders, one of 14 directions in Diffusion models.
- Builds on 33 of its 59 references that are in the map.
- First posted on arXiv 31 Dec 2025.

## Placed in

- Diffusion models / [Diffusion recommenders](https://mlsanity.com/diffusion/diffusion-recommenders/)

## Builds on (most cited first, 30 of 33)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Understanding Diffusion Models: A Unified Perspective](https://mlsanity.com/paper/2208.11970/) (2022)
- [FedDC: Federated Learning with Non-IID Data via Local Drift Decoupling and Correction](https://mlsanity.com/paper/2203.11751/) (2022)
- [MeLU: Meta-Learned User Preference Estimator for Cold-Start Recommendation](https://mlsanity.com/paper/1908.00413/) (2019)
- [Secure Federated Matrix Factorization](https://mlsanity.com/paper/1906.05108/) (2019)
- [DiffuRec: A Diffusion Model for Sequential Recommendation](https://mlsanity.com/paper/2304.00686/) (2023)
- [Diffusion Recommender Model](https://mlsanity.com/paper/2304.04971/) (2023)
- [Federated Collaborative Filtering for Privacy-Preserving Personalized Recommendation System](https://mlsanity.com/paper/1901.09888/) (2019)
- [Contrastive Learning for Cold-Start Recommendation](https://mlsanity.com/paper/2107.05315/) (2021)
- [Item2Vec: Neural Item Embedding for Collaborative Filtering](https://mlsanity.com/paper/1603.04259/) (2016)
- [Diffusion Augmentation for Sequential Recommendation](https://mlsanity.com/paper/2309.12858/) (2023)
- [Federated Neural Collaborative Filtering](https://mlsanity.com/paper/2106.04405/) (2021)
- [LightFR: Lightweight Federated Recommendation with Privacy-preserving Matrix Factorization](https://mlsanity.com/paper/2206.11743/) (2022)
- [DiffMM: Multi-Modal Diffusion Model for Recommendation](https://mlsanity.com/paper/2406.11781/) (2024)
- [NineRec: A Benchmark Dataset Suite for Evaluating Transferable Recommendation](https://mlsanity.com/paper/2309.07705/) (2023)
- [HeteFedRec: Federated Recommender Systems with Model Heterogeneity](https://mlsanity.com/paper/2307.12810/) (2023)
- [RecDiff: Diffusion Model for Social Recommendation](https://mlsanity.com/paper/2406.01629/) (2024)
- [A Survey on Diffusion Models for Recommender Systems](https://mlsanity.com/paper/2409.05033/) (2024)
- [Dual Personalization on Federated Recommendation](https://mlsanity.com/paper/2301.08143/) (2023)
- [Could Small Language Models Serve as Recommenders? Towards Data-centric Cold-start Recommendations](https://mlsanity.com/paper/2306.17256/) (2023)
- [FedSOL: Stabilized Orthogonal Learning with Proximal Restrictions in Federated Learning](https://mlsanity.com/paper/2308.12532/) (2023)
- [Federated Adaptation for Foundation Model-based Recommendations](https://mlsanity.com/paper/2405.04840/) (2024)
- [Learning Graph Meta Embeddings for Cold-Start Ads in Click-Through Rate Prediction](https://mlsanity.com/paper/2105.08909/) (2021)
- [When Federated Recommendation Meets Cold-Start Problem: Separating Item Attributes and User Interactions](https://mlsanity.com/paper/2305.12650/) (2023)
- [Towards Personalized Privacy: User-Governed Data Contribution for Federated Recommendation](https://mlsanity.com/paper/2401.17630/) (2024)
- [Beyond Similarity: Personalized Federated Recommendation with Composite Aggregation](https://mlsanity.com/paper/2406.03933/) (2024)
- [Efficient and Robust Regularized Federated Recommendation](https://mlsanity.com/paper/2411.01540/) (2024)

## Abstract (arXiv)

Federated recommendations (FRs) provide personalized services while preserving user privacy by keeping user data on local clients, which has attracted significant attention in recent years. However, due to the strict privacy constraints inherent in FRs, access to user-item interaction data and user profiles across clients is highly restricted, making it difficult to learn globally effective representations for new (cold-start) items. Consequently, the item cold-start problem becomes even more challenging in FRs. Existing solutions typically predict embeddings for new items through the attribute-to-embedding mapping paradigm, which establishes a fixed one-to-one correspondence between item attributes and their embeddings. However, this one-to-one mapping paradigm often fails to model varying data distributions and tends to cause embedding misalignment, as verified by our empirical studies. To this end, we propose MDiffFR, a novel generation-based modality-guided diffusion method for cold-start items in FRs. In this framework, we employ a tailored diffusion model on the server to generate embeddings for new items, which are then distributed to clients for cold-start inference. To align item semantics, we deploy a pre-trained modality encoder to extract modality features as conditional signals to guide the reverse denoising process. Furthermore, our theoretical analysis verifies that the proposed method achieves stronger privacy guarantees compared to existing mapping-based approaches. Extensive experiments on four real datasets demonstrate that our method consistently outperforms all baselines in FRs.