cs.IROct 12, 2026

OT-FlowRec: Optimal Transport-Guided Multi-Bridge Flow for Multimodal Sequential Recommendation

Authors: Miao Sun

Organizations: Nanjing University of Science and Technology School of Computer Science and Engineering

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

E-commerce user preferences evolve dynamically within sessions, exhibiting concurrent and multi-centric interest distributions. While existing multimodal sequential recommendation methods leverage global attention to compress historical interactions, they inadequately capture the concurrent nature of multi-interest behaviors and fail to model the underlying multi-centric distribution of user intent. To tackle this issue, we propose OT-FlowRec, an optimal transport-guided multi-bridge flow matching framework that explicitly models multi-interest distributions to facilitate multimodal sequential recommendation. Unlike single-path generative models, OT-FlowRec constructs a mixture of parallel, interest-specific transport flows to model the multi-centric distribution characteristics, where each flow preserves a distinct user interest cluster via an optimal transport plan. Then, a geometric transport mechanism is designed to establish minimum-cost paths from the latent multi-interest distribution to target preference prototypes to provide multi-interest awareness. Moreover, a progressive time-sampling warmup strategy dynamically biases optimization weights toward the final states of the generation process, bridging the gap between continuous global distribution fitting and practical top-kk ranking metrics. This approach achieves explicit interest disentanglement, ensuring the preservation of a multi-peaked preference representation instead of collapsing it into a unimodal average. Extensive experiments on three public datasets demonstrate that OT-FlowRec outperforms existing state-of-the-art baselines.

Figures & tables

Figure 1: User interaction paths in the Toys dataset. Colors denote latent interest categories; this shows that multiple interests coexist within a session.
Figure 2: The overall architecture of OT-FlowRec. Top: The end-to-end recommendation pipeline, transforming multimodal item interactions into parallel transport flows. Middle-left: MPSD fuses multimodal features via a softplus gating network and extracts top- kk prototypes to construct parallel interest distributions. Bottom-right: OT-MBFM establishes OT couplings via a geometric cost matrix to guide deterministic flow matching along minimum-cost trajectories. Bottom-left: PTW dynamically shifts time-step sampling weights toward terminal generation states ( t→1t\to 1 ) via Beta distribution adjustments.
DatasetUsersItemsInter.SparsityAvg. Len.
Beauty223641210219850299.92%8.8
Video Games243041067923178099.91%9.5
Toys194131192516759799.92%8.6
Table 1: Statistics of the evaluation datasets.
BaselineBeautyVideo GamesToys
 H@10H@20N@10N@20H@10H@20N@10N@20H@10H@20N@10N@20
SASRec0.04010.06600.02000.02650.08470.12810.04230.05320.03220.04970.01640.0208
GRU4Rec0.05620.08510.02980.03700.07250.11220.03760.04750.04540.06760.02600.0316
BERT4Rec0.03790.05710.02000.02490.07080.10910.03610.04560.02740.03950.01540.0184
MSSR0.05830.09560.03140.04480.07090.12830.04150.05150.06130.09500.03180.0410
DreamRec0.02280.04170.01300.01760.04150.07120.02210.02950.02160.03910.01110.0155
Table 2: Overall performance. The best and second-best scores are shown in bold and underlined, respectively.
Figure 3: Vector field comparison between traditional flow matching and OT-FlowRec on the Toys.
Appendix figures & tables4 assets

Supplementary material from the paper’s appendix.

Appendix

Figure 6
HyperparameterSearch space
Learning rateexp⁡(U[−9.2,−6.0])\exp(\mathcal{U}[-9.2,-6.0])
Number of Transformer layers{1,2,3}\{1,2,3\}
Hidden dimension dd{128,256}\{128,256\}
Hidden dropout / attention dropoutU[0.1,0.5]\mathcal{U}[0.1,0.5]
Number of prototypes MM{32,64,96,128}\{32,64,96,128\}
ODE steps{2,4,6,8}\{2,4,6,8\}
Appendix
Table 4: Hyperparameter search space of OT-FlowRec.
DatasetLRLayersddDrop.Attn Drop.MMODEτ\tauϵOT\epsilon_{\mathrm{OT}}Iter.Warm-upλProto\lambda_{\mathrm{Proto}}λOT\lambda_{\mathrm{OT}}
Beauty5.87×10−45.87{\times}10^{-4}11280.397550.446079660.039190.1205310120.119670.02177
Toys6.322×10−46.322{\times}10^{-4}12560.457300.267359660.023180.11727910120.0568530.02742
Video_Games6.30×10−46.30{\times}10^{-4}21280.495510.3402659660.0844360.081655590.120090.05440
Appendix
Table 5: Best hyperparameters of OT-FlowRec on each dataset.
Figure 6: Validation N@20 curves of OT-FlowRec and the ablation variants
More in this topic

Recommender Systems

Recommender systems predict and rank items for people using interaction histories, content, context, and feedback.

See all 508 papers

Explore similar work

CardsList
Feb 26, 2026

From Agnostic to Specific: Latent Preference Diffusion for Multi-Behavior Sequential Recommendation

Multi-behavior sequential recommendation (MBSR) aims to learn the dynamic and heterogeneous interactions of users' multi-behavior sequences, so as to capture user preferences under target behavior for the next interacted item prediction. Unlike previous methods that adopt unidirectional modeling by mapping auxiliary behaviors to target behavior, recent concerns are shifting from behavior-fixed to behavior-specific recommendation. However, these methods still ignore the user's latent preference that underlying decision-making, leading to suboptimal solutions. Meanwhile, due to the asymmetric deterministic between items and behaviors, discriminative paradigm based on preference scoring is unsuitable to capture the uncertainty from low-entropy behaviors to high-entropy items, failing to provide efficient and diverse recommendation. To address these challenges, we propose FatsMB, a framework based diffusion model that guides preference generation From Behavior-Agnostic To Behavior-Specific in latent spaces, enabling diverse and accurate Multi-Behavior Sequential Recommendation. Specifically, we design a Multi-Behavior AutoEncoder (MBAE) to construct a unified user latent preference space, facilitating interaction and collaboration across Behaviors, within Behavior-aware RoPE (BaRoPE) employed for multiple information fusion. Subsequently, we conduct target behavior-specific preference transfer in the latent space, enriching with informative priors. A Multi-Condition Guided Layer Normalization (MCGLN) is introduced for the denoising. Extensive experiments on real-world datasets demonstrate the effectiveness of our model.

Ruochen Yang, Xiaodong Li, Jiawei Sheng +6

Institute of Information Engineering, Chinese Academy of Sciences · School of Cyber Security, UCAS · Kuaishou Technology

Recommender SystemsSequential RecommendationUser Preference Modeling
AskPDF
Sep 18, 2026

Dual-Interest Sequential Product Recommendation With Multi-Granular SSM

Sequential recommendation aims to predict the next item a user will interact with based on their historical behavior. Advances in Transformers have significantly improved sequential recommendation but are still limited by cost efficiency. Although State Space Models (SSMs) have recently enabled efficient long-range modeling, most existing methods encode each item with a single static contextual role, overlooking the phenomenon of item polysemy. In fact, the same item often plays different semantic roles depending on user context, and existing methods are limited in capturing dynamic behavior across different temporal granularities. In this work, we propose DSRec, a novel dual-interest cross-SSM model that explicitly disentangles item roles across long-term and short-term semantic context. Sequential items are encoded into long-term interest embeddings that capture stable preferences via historical aggregation, and a short-term interest branch that emphasizes local session intent modulated by inter-click time intervals. These interest embeddings are processed through distinct SSM encoders: a full-sequence Mamba for long-term modeling, and a time-modulated SSM that dynamically adjusts state evolution based on temporal gaps. To enable effective cross-granularity alignment, we adopt a residual cross-fusion mechanism that exchanges contextual information between the two branches while preserving semantic independence. Experiments on public benchmarks demonstrate that DSRec outperforms other state-of-the-art methods.

Shuiying Liao, P. Y. Mok

The Hong Kong University of Science and Technology Clear Water Bay, Hong Kong

Sequential RecommendationUser Preference ModelingSelective SSMs
AskPDF
Oct 8, 2026

Multimodal Graph Retrieval-Augmented Sequential Recommendation via Collaborative Filtering Paths

Multimodal Large Language Models (MLLMs) have demonstrated strong potential for sequential recommendation through their ability to reason over complex multimodal data. However, existing approaches either rely solely on the target user's own interaction history, neglecting collaborative signals from neighboring users, or incur substantial computational overhead through repeated MLLM inference over long interaction histories. To address these challenges, we propose MGRASRec, a multimodal graph retrieval-augmented framework for sequential recommendation. MGRASRec injects collaborative filtering signals conditioned on the candidate item directly into the MLLM prompt by retrieving structured paths from a user-item interaction graph, extended via multimodal similarity to increase coverage beyond exact co-interaction overlap. This retrieval also surfaces the history items most relevant to the candidate at no additional cost, removing the need for recurrent summarization and keeping inference to a single forward pass per candidate. All components are unified into an augmented prompt for parameter-efficient fine-tuning of an MLLM. Extensive evaluations across three publicly available datasets validate the effectiveness of MGRASRec, achieving the best performance on all metrics with particularly strong gains in ranking quality.

Jason Marcell Setiadi, Xin Cao, Lina Yao

University of New South Wales, Sydney, Australia

Recommender SystemsSequential RecommendationMultimodal RecommendationLarge Language Model-Based Recommendation
AskPDF