pith. machine review for the scientific record. sign in

arxiv: 2604.05365 · v1 · submitted 2026-04-07 · 💻 cs.IR

Recognition: 2 theorem links

· Lean Theorem

From Clues to Generation: Language-Guided Conditional Diffusion for Cross-Domain Recommendation

Ziang Lu , Lei Sang , Lin Mu , Yiwen Zhang
Authors on Pith no claims yet

Pith reviewed 2026-05-10 19:32 UTC · model grok-4.3

classification 💻 cs.IR
keywords cross-domain recommendationinter-domain recommendationconditional diffusionlarge language modelspseudo-interactionssequential recommendationpreference transfer
0
0 comments X

The pith

LGCD uses LLMs to build pseudo user overlaps and conditional diffusion to generate target representations for inter-domain recommendation without shared users.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper targets inter-domain recommendation where users interact in one domain but have no records in another, making direct transfer hard without overlapping users. It proposes the LGCD framework that applies LLM reasoning to infer likely target-domain preferences from source data and map them onto real items, thereby creating synthetic overlapping users. Supervision constraints are added to separate real and pseudo pathways and limit noise from the generated data. A conditional diffusion model then takes source-domain patterns as conditioning input to produce precise target user representations for sequential recommendation. Experiments on standard benchmarks show this combination beats prior state-of-the-art approaches.

Core claim

The central claim is that LLM reasoning can construct usable pseudo-overlapping data by inferring target preferences for single-domain users and mapping them to real items; when this data is paired with supervision constraints and fed into a conditional diffusion architecture that generates target user representations guided by source patterns, accurate inter-domain sequential recommendation becomes possible even when real overlapping users are scarce.

What carries the argument

The Language-Guided Conditional Diffusion (LGCD) framework, which treats LLM-generated pseudo-interactions as anchors for domain bridging while using a conditional diffusion process to model and generate target representations from source-domain inputs.

If this is right

  • Distinguishing real interaction pathways from pseudo ones with extra supervision reduces the impact of semantic noise on transferred preferences.
  • Conditioning a diffusion model on source-domain patterns produces more precise target user representations than direct mapping methods.
  • LLM-based inference of target preferences can serve as a scalable substitute for scarce real overlapping users in cross-domain settings.
  • The overall pipeline yields measurable gains in sequential recommendation accuracy for users lacking target-domain history.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same LLM-plus-diffusion pattern could be tested in cold-start recommendation scenarios where no prior user data exists in either domain.
  • If the quality of pseudo-interactions can be validated without extra supervision, the framework might simplify to a fully generative transfer approach.
  • Diffusion models may prove especially useful for other generative tasks in recommendation that require smooth interpolation between domain-specific patterns.

Load-bearing premise

That LLM-generated pseudo-interactions provide sufficiently accurate and low-noise signals for preference transfer, even after adding supervision constraints to mitigate semantic noise.

What would settle it

Replacing the LLM inference step with random item mapping or heuristic rules and observing that recommendation accuracy on single-domain users falls back to the level of non-transfer baselines would falsify the claim that the pseudo data supplies reliable transfer signals.

Figures

Figures reproduced from arXiv: 2604.05365 by Lei Sang, Lin Mu, Yiwen Zhang, Ziang Lu.

Figure 1
Figure 1. Figure 1: The core idea of LGCD to realistic single-domain user scenarios with scarce over￾lapping users. • We introduce an LLM-driven pseudo-overlap construction mechanism to synthesize anchors, complemented by a decou￾pled training strategy with cyclic batching. This approach effectively augments preferences using pseudo interactions while mitigating semantic noise by prioritizing real overlap￾ping data for alignm… view at source ↗
Figure 2
Figure 2. Figure 2: The overall framework of LGCD, illustrating the complete workflow with domain A as the source and domain B as the [PITH_FULL_IMAGE:figures/full_fig_p004_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Impact of the hyper-parameters 𝑛𝐾 , 𝑛shared, 𝑛specific on the Movie-Book and Food-Kitchen datasets. the source domain and fully leverages the target-domain features generated by the diffusion model, thereby achieving superior cross￾domain mapping and alignment of long-term user preferences. 4.3.2 Hyper-parameter Sensitivities. To investigate the impact of hyperparameters, we analyze the model’s sensitivity… view at source ↗
Figure 5
Figure 5. Figure 5: The impact of different training targets for diffusion [PITH_FULL_IMAGE:figures/full_fig_p009_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: The influence of overlap ratio on Movie-Book and [PITH_FULL_IMAGE:figures/full_fig_p009_6.png] view at source ↗
read the original abstract

Cross-domain Recommendation (CDR) exploits multi-domain correlations to alleviate data sparsity. As a core task within this field, inter-domain recommendation focuses on predicting preferences for users who interact in a source domain but lack behavioral records in a target domain. Existing approaches predominantly rely on overlapping users as anchors for knowledge transfer. In real-world scenarios, overlapping users are often scarce, leaving the vast majority of users with only single-domain interactions. For these users, the absence of explicit alignment signals makes fine-grained preference transfer intrinsically difficult. To address this challenge, this paper proposes Language-Guided Conditional Diffusion for CDR (LGCD), a novel framework that integrates Large Language Models (LLMs) and diffusion models for inter-domain sequential recommendation. Specifically, we leverage LLM reasoning to bridge the domain gap by inferring potential target preferences for single-domain users and mapping them to real items, thereby constructing pseudo-overlapping data. We distinguish between real and pseudo-interaction pathways and introduce additional supervision constraints to mitigate the semantic noise brought by pseudo-interaction. Furthermore, we design a conditional diffusion architecture to precisely guide the generation of target user representations based on source-domain patterns. Extensive experiments demonstrate that LGCD significantly outperforms state-of-the-art methods in inter-domain recommendation tasks.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 1 minor

Summary. This paper proposes LGCD, a framework for inter-domain sequential recommendation in cross-domain settings. It uses LLMs to infer target-domain preferences for single-domain users and map them to real items, thereby constructing pseudo-overlapping data; distinguishes real and pseudo pathways with added supervision constraints to reduce semantic noise; and employs a conditional diffusion architecture to generate target user representations guided by source-domain patterns. The central claim is that LGCD significantly outperforms state-of-the-art methods.

Significance. If the claims hold, particularly the reliability of LLM-generated pseudo-interactions for preference transfer, the work could meaningfully advance cross-domain recommendation by addressing the practical scarcity of overlapping users. The integration of LLM reasoning for domain bridging with conditional diffusion for representation generation offers a novel technical direction that may improve performance in sparse multi-domain scenarios.

major comments (2)
  1. [Abstract] Abstract: the assertion that 'Extensive experiments demonstrate that LGCD significantly outperforms state-of-the-art methods' is unsupported by any quantitative results, error bars, dataset details, or ablation studies, which are required to evaluate the central outperformance claim.
  2. [Method] Method section (pseudo-overlapping data construction): the framework relies on LLM-inferred target preferences as transfer anchors without an independent quantitative check (e.g., precision@K of inferred items on held-out overlapping users) to confirm that the pseudo-labels supply reliable low-noise signals rather than noise that the diffusion model merely fits.
minor comments (1)
  1. The abstract would benefit from briefly naming the key metrics and datasets to contextualize the outperformance claim.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive feedback on our manuscript. The comments highlight important aspects of clarity in the abstract and validation of the pseudo-data construction. We address each point below and will incorporate revisions to strengthen the paper.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the assertion that 'Extensive experiments demonstrate that LGCD significantly outperforms state-of-the-art methods' is unsupported by any quantitative results, error bars, dataset details, or ablation studies, which are required to evaluate the central outperformance claim.

    Authors: We agree that the abstract, being a high-level summary, does not embed specific quantitative results, error bars, or dataset details. The full manuscript presents these in the Experiments section, including performance tables with standard deviations, dataset statistics, and ablation studies. To directly address the concern, we will revise the abstract to include concise quantitative highlights (e.g., average relative improvements and dataset references) while respecting length limits, thereby better supporting the outperformance claim. revision: yes

  2. Referee: [Method] Method section (pseudo-overlapping data construction): the framework relies on LLM-inferred target preferences as transfer anchors without an independent quantitative check (e.g., precision@K of inferred items on held-out overlapping users) to confirm that the pseudo-labels supply reliable low-noise signals rather than noise that the diffusion model merely fits.

    Authors: We acknowledge the value of an independent validation for the LLM-generated pseudo-interactions to confirm signal quality. The current manuscript mitigates noise via explicit supervision constraints that differentiate real and pseudo pathways (Section 3.3). However, we did not report a direct precision@K check on held-out overlapping users. In the revision, we will add this evaluation using any available overlapping users in the datasets to quantify inference accuracy and demonstrate that the pseudo-labels provide reliable anchors rather than noise. revision: yes

Circularity Check

0 steps flagged

No circularity; framework is methodologically independent of its outputs

full rationale

The paper introduces LGCD by describing LLM-based pseudo-interaction generation followed by conditional diffusion training with supervision constraints. No equations, derivations, or self-referential definitions appear in the provided text that would reduce any claimed prediction or result to its own inputs by construction. The pseudo-data pathway is an external generative step whose accuracy is asserted to be mitigated by constraints, with outperformance resting on experimental results rather than tautological fitting or self-citation chains. This qualifies as a self-contained methodological proposal.

Axiom & Free-Parameter Ledger

0 free parameters · 2 axioms · 0 invented entities

Framework depends on LLM reasoning to produce usable pseudo-preferences and on diffusion models learning conditional distributions from source patterns; no explicit free parameters or invented entities listed in abstract.

axioms (2)
  • domain assumption LLMs can reliably infer plausible target-domain preferences from source-domain behavior for single-domain users
    Core step for constructing pseudo-overlapping data
  • domain assumption Conditional diffusion can precisely map source patterns to target user representations when guided by pseudo data
    Central to the generation architecture

pith-pipeline@v0.9.0 · 5523 in / 1257 out tokens · 92047 ms · 2026-05-10T19:32:48.748916+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. DIAURec: Dual-Intent Space Representation Optimization for Recommendation

    cs.IR 2026-04 unverdicted novelty 5.0

    DIAURec unifies intent and language modeling to reconstruct and optimize representations in prototype and distribution spaces, outperforming baselines on three datasets.

Reference graph

Works this paper leans on

58 extracted references · 9 canonical work pages · cited by 1 Pith paper · 4 internal anchors

  1. [1]

    Jiangxia Cao, Xin Cong, Jiawei Sheng, Tingwen Liu, and Bin Wang. 2022. Con- trastive cross-domain sequential recommendation. InProceedings of the 31st ACM International Conference on Information & Knowledge Management. 138–147

    2022

  2. [2]

    Jiangxia Cao, Shaoshuai Li, Bowen Yu, Xiaobo Guo, Tingwen Liu, and Bin Wang

  3. [3]

    InProceedings of the Sixteenth ACM International Conference on web search and data mining

    Towards universal cross-domain recommendation. InProceedings of the Sixteenth ACM International Conference on web search and data mining. 78–86

  4. [4]

    Jiangxia Cao, Jiawei Sheng, Xin Cong, Tingwen Liu, and Bin Wang. 2022. Cross- domain recommendation to cold-start users via variational information bottle- neck. In2022 IEEE 38th International Conference on data engineering (ICDE). IEEE, 2209–2223

    2022

  5. [5]

    Shu Chen, Zitao Xu, Weike Pan, Qiang Yang, and Zhong Ming. 2024. A survey on cross-domain sequential recommendation.arXiv preprint arXiv:2401.04971 (2024)

    work page arXiv 2024

  6. [6]

    Weixin Chen, Yuhan Zhao, Li Chen, and Weike Pan. 2025. Leave No One Be- hind: Fairness-Aware Cross-Domain Recommender Systems for Non-Overlapping Users. InProceedings of the Nineteenth ACM Conference on Recommender Systems. 226–236

    2025

  7. [7]

    Florinel-Alin Croitoru, Vlad Hondru, Radu Tudor Ionescu, and Mubarak Shah

  8. [8]

    Diffusion models in vision: A survey.IEEE transactions on pattern analysis and machine intelligence45, 9 (2023), 10850–10869

    2023

  9. [9]

    Xinyu Du, Huanhuan Yuan, Pengpeng Zhao, Jianfeng Qu, Fuzhen Zhuang, Guan- feng Liu, Yanchi Liu, and Victor S Sheng. 2023. Frequency enhanced hybrid attention network for sequential recommendation. InProceedings of the 46th international ACM SIGIR conference on research and development in information retrieval. 78–88

    2023

  10. [10]

    Lei Guo, Hao Liu, Lei Zhu, Weili Guan, and Zhiyong Cheng. 2023. DA-DAN: A dual adversarial domain adaption network for unsupervised non-overlapping cross-domain recommendation.ACM Transactions on Information Systems42, 2 (2023), 1–27

    2023

  11. [11]

    Lei Guo, Chunxiao Wang, Xinhua Wang, Lei Zhu, and Hongzhi Yin. 2025. Auto- mated prompting for non-overlapping cross-domain sequential recommendation. IEEE Transactions on Knowledge and Data Engineering(2025)

    2025

  12. [12]

    Balázs Hidasi, Alexandros Karatzoglou, Linas Baltrunas, and Domonkos Tikk

  13. [13]

    Session-based recommendations with recurrent neural networks.arXiv preprint arXiv:1511.06939(2015)

    work page internal anchor Pith review arXiv 2015

  14. [14]

    Jonathan Ho and Tim Salimans. 2022. Classifier-free diffusion guidance.arXiv preprint arXiv:2207.12598(2022)

    work page internal anchor Pith review Pith/arXiv arXiv 2022

  15. [15]

    Yupeng Hou, Shanlei Mu, Wayne Xin Zhao, Yaliang Li, Bolin Ding, and Ji-Rong Wen. 2022. Towards universal sequence representation learning for recommender systems. InProceedings of the 28th ACM SIGKDD conference on knowledge discovery and data mining. 585–593

    2022

  16. [16]

    Lei Huang, Weijiang Yu, Weitao Ma, Weihong Zhong, Zhangyin Feng, Haotian Wang, Qianglong Chen, Weihua Peng, Xiaocheng Feng, Bing Qin, et al. 2025. A survey on hallucination in large language models: Principles, taxonomy, chal- lenges, and open questions.ACM Transactions on Information Systems43, 2 (2025), 1–55

    2025

  17. [17]

    Ke Jin, Weihao Yu, Yingchao Long, Nanhui Lai, and Jin Huang. 2025. A diffusion multi-interest framework for cross-domain recommendation.Expert Systems with Applications(2025), 128738

    2025

  18. [18]

    SeongKu Kang, Junyoung Hwang, Dongha Lee, and Hwanjo Yu. 2019. Semi- supervised learning for cross-domain recommendation to cold-start users. In Proceedings of the 28th ACM international conference on information and knowledge management. 1563–1572

    2019

  19. [19]

    Wang-Cheng Kang and Julian McAuley. 2018. Self-attentive sequential recom- mendation. In2018 IEEE international conference on data mining (ICDM). IEEE, 197–206

    2018

  20. [20]

    Sein Kim, Hongseok Kang, Kibum Kim, Jiwan Kim, Donghyun Kim, Minchul Yang, Kwangjin Oh, Julian McAuley, and Chanyoung Park. 2025. Lost in Sequence: Do Large Language Models Understand Sequential Recommendation?. InProceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V

    2025

  21. [21]

    Diederik P Kingma. 2014. Adam: A method for stochastic optimization.arXiv preprint arXiv:1412.6980(2014)

    work page internal anchor Pith review Pith/arXiv arXiv 2014

  22. [22]

    Fengxin Li, Hongyan Liu, and Jun He. 2025. Diffusion Alignment for Cross Domain Recommendation. InProceedings of the 2025 International Conference on Multimedia Retrieval. 715–723

    2025

  23. [23]

    Hanyu Li, Jiayu Li, Weizhi Ma, Peijie Sun, Haiyang Wu, Jingwen Wang, Yuekui Yang, Min Zhang, and Shaoping Ma. 2025. CD-CDR: Conditional Diffusion-based Item Generation for Cross-Domain Recommendation. InProceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval. 1789–1798

    2025

  24. [24]

    Hanyu Li, Weizhi Ma, Peijie Sun, Jiayu Li, Cunxiang Yin, Yancheng He, Guoqiang Xu, Min Zhang, and Shaoping Ma. 2024. Aiming at the target: Filter collabora- tive information for cross-domain recommendation. InProceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval. 2081–2090

    2024

  25. [25]

    Hourun Li, Yifan Wang, Zhiping Xiao, Jia Yang, Changling Zhou, Ming Zhang, and Wei Ju. 2025. DisCo: graph-based disentangled contrastive learning for cold-start cross-domain recommendation. InProceedings of the AAAI Conference on Artificial Intelligence, Vol. 39. 12049–12057

    2025

  26. [26]

    Lei Li, Yongfeng Zhang, Dugang Liu, and Li Chen. 2024. Large language models for generative recommendation: A survey and visionary discussions. InProceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024). 10146–10159

    2024

  27. [27]

    Pan Li and Alexander Tuzhilin. 2020. Ddtcdr: Deep dual transfer cross domain recommendation. InProceedings of the 13th international conference on web search and data mining. 331–339

    2020

  28. [28]

    Tianhong Li and Kaiming He. 2025. Back to basics: Let denoising generative models denoise.arXiv preprint arXiv:2511.13720(2025)

    work page internal anchor Pith review arXiv 2025

  29. [29]

    Xiaodong Li, Jiawei Sheng, Jiangxia Cao, Wenyuan Zhang, Quangang Li, and Tingwen Liu. 2024. Cdrnp: Cross-domain recommendation to cold-start users via neural process. InProceedings of the 17th ACM international conference on web search and data mining. 378–386

    2024

  30. [30]

    Xiaodong Li, Hengzhu Tang, Jiawei Sheng, Xinghua Zhang, Li Gao, Suqi Cheng, Dawei Yin, and Tingwen Liu. 2025. Exploring Preference-Guided Diffusion Model for Cross-Domain Recommendation.arXiv preprint arXiv:2501.11671(2025)

    work page arXiv 2025

  31. [31]

    Zhi Li, Daichi Amagata, Yihong Zhang, Takahiro Hara, Shuichiro Haruta, Kei Yonekawa, and Mori Kurokawa. 2024. Mutual information-based preference disentangling and transferring for non-overlapped multi-target cross-domain recommendations. InProceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval. 2124–2133

    2024

  32. [32]

    Zihao Li, Aixin Sun, and Chenliang Li. 2023. Diffurec: A diffusion model for sequential recommendation.ACM Transactions on Information Systems42, 3 (2023), 1–28

    2023

  33. [33]

    Guanyu Lin, Chen Gao, Yu Zheng, Jianxin Chang, Yanan Niu, Yang Song, Kun Gai, Zhiheng Li, Depeng Jin, Yong Li, et al . 2024. Mixed attention network for cross-domain sequential recommendation. InProceedings of the 17th ACM international conference on web search and data mining. 405–413

    2024

  34. [34]

    Hao Liu, Lei Guo, Lei Zhu, Yongqiang Jiang, Min Gao, and Hongzhi Yin. 2024. MCRPL: A Pretrain, prompt, and fine-tune paradigm for non-overlapping many- to-one cross-domain recommendation.ACM Transactions on Information Systems 42, 4 (2024), 1–24

    2024

  35. [35]

    Kuan Liu, Ke Wang, Ji Zhang, and Gang Zhou. 2025. LLM-Grounded Diffusion for Cross-Domain Recommendation. InProceedings of the 33rd ACM International Conference on Multimedia. 6103–6112

    2025

  36. [36]

    Qidong Liu, Fan Yan, Xiangyu Zhao, Zhaocheng Du, Huifeng Guo, Ruiming Tang, and Feng Tian. 2023. Diffusion augmentation for sequential recommenda- tion. InProceedings of the 32nd ACM International conference on information and knowledge management. 1576–1586

    2023

  37. [37]

    Haokai Ma, Ruobing Xie, Lei Meng, Xin Chen, Xu Zhang, Leyu Lin, and Zhan- hui Kang. 2024. Plug-in diffusion model for sequential recommendation. In Proceedings of the AAAI conference on artificial intelligence, Vol. 38. 8886–8894

    2024

  38. [38]

    Haokai Ma, Ruobing Xie, Lei Meng, Xin Chen, Xu Zhang, Leyu Lin, and Jie Zhou. 2024. Triple sequence learning for cross-domain recommendation.ACM Transactions on Information Systems42, 4 (2024), 1–29

    2024

  39. [39]

    Tong Man, Huawei Shen, Xiaolong Jin, and Xueqi Cheng. 2017. Cross-domain recommendation: An embedding and mapping approach.. InIjcai, Vol. 17. 2464– 2470

    2017

  40. [40]

    Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, and Björn Ommer. 2022. High-resolution image synthesis with latent diffusion models. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 10684–10695. LGCD SIGIR ’26, July 20–24, 2026, Melbourne, VIC, Australia

    2022

  41. [41]

    SMTI Tonmoy, SM Zaman, Vinija Jain, Anku Rani, Vipula Rawte, Aman Chadha, and Amitava Das. 2024. A comprehensive survey of hallucination mitigation techniques in large language models.arXiv preprint arXiv:2401.013136 (2024)

    work page arXiv 2024

  42. [42]

    Anwaar Ulhaq and Naveed Akhtar. 2022. Efficient diffusion models for vision: A survey.arXiv preprint arXiv:2210.09292(2022)

    work page arXiv 2022

  43. [43]

    Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need.Advances in neural information processing systems30 (2017)

    2017

  44. [44]

    Yu Wang, Zhiwei Liu, Liangwei Yang, and Philip S Yu. 2024. Conditional denoising diffusion for sequential recommendation. InPacific-Asia conference on knowledge discovery and data mining. Springer, 156–169

    2024

  45. [45]

    Zihan Wang, Yonghui Yang, Le Wu, Richang Hong, and Meng Wang. 2024. Mak- ing Non-Overlapping Matters: An Unsupervised Alignment Enhanced Cross- Domain Cold-Start Recommendation.IEEE Transactions on Knowledge and Data Engineering(2024)

    2024

  46. [46]

    Likang Wu, Zhi Zheng, Zhaopeng Qiu, Hao Wang, Hongchao Gu, Tingjia Shen, Chuan Qin, Chen Zhu, Hengshu Zhu, Qi Liu, et al . 2024. A survey on large language models for recommendation.World Wide Web27, 5 (2024), 60

    2024

  47. [47]

    Haoran Xin, Ying Sun, Chao Wang, and Hui Xiong. 2025. Llmcdsr: Enhancing cross-domain sequential recommendation with large language models.ACM Transactions on Information Systems(2025)

    2025

  48. [48]

    Zitao Xu, Shu Chen, Weike Pan, and Zhong Ming. 2025. A multi-view graph contrastive learning framework for cross-domain sequential recommendation. ACM Transactions on Recommender Systems3, 4 (2025), 1–28

    2025

  49. [49]

    Yuner Xuan. 2024. Diffusion cross-domain recommendation.arXiv preprint arXiv:2402.02182(2024)

    work page arXiv 2024

  50. [50]

    Ling Yang, Zhilong Zhang, Zhaochen Yu, Jingwei Liu, Minkai Xu, Stefano Ermon, and Bin Cui. 2024. Cross-modal contextualized diffusion models for text-guided visual generation and editing. InThe Twelfth International Conference on Learning Representations

    2024

  51. [51]

    Wenhao Yang, Yingchun Jian, Yibo Wang, Shiyin Lu, Lei Shen, Bing Wang, Hai- hong Tang, and Lijun Zhang. 2024. Not all embeddings are created equal: towards robust cross-domain recommendation via contrastive learning. InProceedings of the ACM Web Conference 2024. 3195–3206

    2024

  52. [52]

    Zhengyi Yang, Jiancan Wu, Zhicai Wang, Xiang Wang, Yancheng Yuan, and Xiangnan He. 2023. Generate what you prefer: Reshaping sequential recommen- dation via guided diffusion.Advances in Neural Information Processing Systems 36 (2023), 24247–24261

    2023

  53. [53]

    Tianzi Zang, Yanmin Zhu, Haobing Liu, Ruohan Zhang, and Jiadi Yu. 2022. A survey on cross-domain recommendation: taxonomies, methods, and future directions.ACM Transactions on Information Systems41, 2 (2022), 1–39

    2022

  54. [54]

    Chuang Zhao, Hongke Zhao, Ming He, Jian Zhang, and Jianping Fan. 2023. Cross- domain recommendation via user interest alignment. InProceedings of the ACM web conference 2023. 887–896

    2023

  55. [55]

    Donglin Zhou, Xinbei Cai, and Weike Pan. 2025. Contrastive Text-enhanced Transformer for Cross-Domain Sequential Recommendation. InProceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V. 2. 4110–4119

    2025

  56. [56]

    Feng Zhu, Chaochao Chen, Yan Wang, Guanfeng Liu, and Xiaolin Zheng. 2019. Dtcdr: A framework for dual-target cross-domain recommendation. InProceed- ings of the 28th ACM international conference on information and knowledge management. 1533–1542

    2019

  57. [57]

    Yongchun Zhu, Kaikai Ge, Fuzhen Zhuang, Ruobing Xie, Dongbo Xi, Xu Zhang, Leyu Lin, and Qing He. 2021. Transfer-meta framework for cross-domain recom- mendation to cold-start users. InProceedings of the 44th international ACM SIGIR conference on research and development in information retrieval. 1813–1817

    2021

  58. [58]

    Yongchun Zhu, Zhenwei Tang, Yudan Liu, Fuzhen Zhuang, Ruobing Xie, Xu Zhang, Leyu Lin, and Qing He. 2022. Personalized transfer of user preferences for cross-domain recommendation. InProceedings of the fifteenth ACM international conference on web search and data mining. 1507–1515

    2022