# MergeRec: Model Merging for Data-Isolated Cross-Domain Sequential Recommendation

arXiv: https://arxiv.org/abs/2601.01753 · HTML: https://mlsanity.com/paper/2601.01753/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 37 of its 50 references that are in the map.
- First posted on arXiv 5 Jan 2026.

## Builds on (most cited first, 30 of 37)

- [Self-Attentive Sequential Recommendation](https://mlsanity.com/paper/1808.09781/) (2018)
- [BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer](https://mlsanity.com/paper/1904.06690/) (2019)
- [TIES-Merging: Resolving Interference When Merging Models](https://mlsanity.com/paper/2306.01708/) (2023)
- [A Primer in BERTology: What we know about how BERT works](https://mlsanity.com/paper/2002.12327/) (2020)
- [Robust fine-tuning of zero-shot models](https://mlsanity.com/paper/2109.01903/) (2021)
- [Session-based Recommendations with Recurrent Neural Networks](https://mlsanity.com/paper/1511.06939/) (2015)
- [Merging Models with Fisher-Weighted Averaging](https://mlsanity.com/paper/2111.09832/) (2021)
- [ZipIt! Merging Models from Different Tasks without Training](https://mlsanity.com/paper/2305.03053/) (2023)
- [Text Is All You Need: Learning Language Representations for Sequential Recommendation](https://mlsanity.com/paper/2305.13731/) (2023)
- [Task Singular Vectors: Reducing Task Interference in Model Merging](https://mlsanity.com/paper/2412.00081/) (2024)
- [Localizing Task Information for Improved Model Merging and Compression](https://mlsanity.com/paper/2405.07813/) (2024)
- [Twin-Merging: Dynamic Integration of Modular Expertise in Model Merging](https://mlsanity.com/paper/2406.15479/) (2024)
- [EMR-Merging: Tuning-Free High-Performance Model Merging](https://mlsanity.com/paper/2405.17461/) (2024)
- [Controllable Multi-Interest Framework for Recommendation](https://mlsanity.com/paper/2005.09347/) (2020)
- [Parameter Competition Balancing for Model Merging](https://mlsanity.com/paper/2410.02396/) (2024)
- [How Does BERT Answer Questions? A Layer-Wise Analysis of Transformer Representations](https://mlsanity.com/paper/1909.04925/) (2019)
- [Knowledge Composition using Task Vectors with Learned Anisotropic Scaling](https://mlsanity.com/paper/2407.02880/) (2024)
- [Training-Free Pretrained Model Merging](https://mlsanity.com/paper/2403.01753/) (2024)
- [Contrastive Cross-Domain Sequential Recommendation](https://mlsanity.com/paper/2304.03891/) (2023)
- [AutoMLP: Automated MLP for Sequential Recommendations](https://mlsanity.com/paper/2303.06337/) (2023)
- [Mixed Information Flow for Cross-domain Sequential Recommendations](https://mlsanity.com/paper/2012.00485/) (2020)
- [MLP4Rec: A Pure MLP Architecture for Sequential Recommendations](https://mlsanity.com/paper/2204.11510/) (2022)
- [Re4: Learning to Re-contrast, Re-attend, Re-construct for Multi-interest Recommendation](https://mlsanity.com/paper/2208.08011/) (2022)
- [A Survey on Cross-Domain Sequential Recommendation](https://mlsanity.com/paper/2401.04971/) (2024)
- [Mixed Attention Network for Cross-domain Sequential Recommendation](https://mlsanity.com/paper/2311.08272/) (2023)
- [Bridge the Domains: Large Language Models Enhanced Cross-domain Sequential Recommendation](https://mlsanity.com/paper/2504.18383/) (2025)
- [Fine-Tuning Attention Modules Only: Enhancing Weight Disentanglement in Task Arithmetic](https://mlsanity.com/paper/2407.07089/) (2024)
- [Pacer and Runner: Cooperative Learning Framework between Single- and Cross-Domain Sequential Recommendation](https://mlsanity.com/paper/2407.11245/) (2024)
- [Bias Vector: Mitigating Biases in Language Models with Task Arithmetic Approach](https://mlsanity.com/paper/2412.11679/) (2024)
- [When Multi-Level Meets Multi-Interest: A Multi-Grained Neural Model for Sequential Recommendation](https://mlsanity.com/paper/2205.01286/) (2022)

## Abstract (arXiv)

Modern recommender systems trained on domain-specific data often struggle to generalize across multiple domains. Cross-domain sequential recommendation has emerged as a promising research direction to address this challenge; however, existing approaches face fundamental limitations, such as reliance on overlapping users or items across domains, or unrealistic assumptions that ignore privacy constraints. In this work, we propose a new framework, MergeRec, based on model merging under a new and realistic problem setting termed data-isolated cross-domain sequential recommendation, where raw user interaction data cannot be shared across domains. MergeRec consists of three key components: (1) merging initialization, (2) pseudo-user data construction, and (3) collaborative merging optimization. First, we initialize a merged model using training-free merging techniques. Next, we construct pseudo-user data by treating each item as a virtual sequence in each domain, enabling the synthesis of meaningful training samples without relying on real user interactions. Finally, we optimize domain-specific merging weights through a joint objective that combines a recommendation loss, which encourages the merged model to identify relevant items, and a distillation loss, which transfers collaborative filtering signals from the fine-tuned source models. Extensive experiments demonstrate that MergeRec not only preserves the strengths of the original models but also significantly enhances generalizability to unseen domains. Compared to conventional model merging methods, MergeRec consistently achieves superior performance, with average improvements of up to 17.21% in Recall@10, highlighting the potential of model merging as a scalable and effective approach for building universal recommender systems. The source code is available at https://github.com/DIALLab-SKKU/MergeRec.