i$^2$VAE: Interest Information Augmentation with Variational Regularizers for Cross-Domain Sequential Recommendation

Xuying Ning, Wujiang Xu, Tianxin Wei, Xiaolei Liu
Proceedings of the Forty-first Conference on Uncertainty in Artificial Intelligence, PMLR 286:3235-3251, 2025.

Abstract

Cross-Domain Sequential Recommendation (CDSR) leverages user behaviors across multiple domains to mitigate data sparsity and cold-start challenges in Single-Domain Sequential Recommendation. Existing methods primarily rely on shared users (overlapping users) to learn transferable interest representations. However, these approaches have limited information propagation, benefiting mainly overlapping users and those with rich interaction histories while neglecting non-overlapping (cold-start) and long-tailed users, who constitute the majority in real-world scenarios. To address this issue, we propose i$^2$VAE, a novel variational autoencoder (VAE)-based framework that enhances user interest learning with mutual information-based regularizers. i$^2$VAE improves recommendations for cold-start and long-tailed users while maintaining strong performance across all user groups. Specifically, cross-domain and disentangling regularizers extract transferable features for cold-start users, while a pseudo-sequence generator synthesizes interactions for long-tailed users, refined by a denoising regularizer to filter noise and preserve meaningful interest signals. Extensive experiments demonstrate that i$^2$VAE outperforms state-of-the-art methods, underscoring its effectiveness in real-world CDSR applications. Code and datasets are available at https://github.com/WujiangXu/IM-VAE.

Cite this Paper

BibTeX
@InProceedings{pmlr-v286-ning25a, title = {i$^2$VAE: Interest Information Augmentation with Variational Regularizers for Cross-Domain Sequential Recommendation}, author = {Ning, Xuying and Xu, Wujiang and Wei, Tianxin and Liu, Xiaolei}, booktitle = {Proceedings of the Forty-first Conference on Uncertainty in Artificial Intelligence}, pages = {3235--3251}, year = {2025}, editor = {Chiappa, Silvia and Magliacane, Sara}, volume = {286}, series = {Proceedings of Machine Learning Research}, month = {21--25 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v286/main/assets/ning25a/ning25a.pdf}, url = {https://proceedings.mlr.press/v286/ning25a.html}, abstract = {Cross-Domain Sequential Recommendation (CDSR) leverages user behaviors across multiple domains to mitigate data sparsity and cold-start challenges in Single-Domain Sequential Recommendation. Existing methods primarily rely on shared users (overlapping users) to learn transferable interest representations. However, these approaches have limited information propagation, benefiting mainly overlapping users and those with rich interaction histories while neglecting non-overlapping (cold-start) and long-tailed users, who constitute the majority in real-world scenarios. To address this issue, we propose i$^2$VAE, a novel variational autoencoder (VAE)-based framework that enhances user interest learning with mutual information-based regularizers. i$^2$VAE improves recommendations for cold-start and long-tailed users while maintaining strong performance across all user groups. Specifically, cross-domain and disentangling regularizers extract transferable features for cold-start users, while a pseudo-sequence generator synthesizes interactions for long-tailed users, refined by a denoising regularizer to filter noise and preserve meaningful interest signals. Extensive experiments demonstrate that i$^2$VAE outperforms state-of-the-art methods, underscoring its effectiveness in real-world CDSR applications. Code and datasets are available at https://github.com/WujiangXu/IM-VAE.} }
Endnote
%0 Conference Paper %T i$^2$VAE: Interest Information Augmentation with Variational Regularizers for Cross-Domain Sequential Recommendation %A Xuying Ning %A Wujiang Xu %A Tianxin Wei %A Xiaolei Liu %B Proceedings of the Forty-first Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2025 %E Silvia Chiappa %E Sara Magliacane %F pmlr-v286-ning25a %I PMLR %P 3235--3251 %U https://proceedings.mlr.press/v286/ning25a.html %V 286 %X Cross-Domain Sequential Recommendation (CDSR) leverages user behaviors across multiple domains to mitigate data sparsity and cold-start challenges in Single-Domain Sequential Recommendation. Existing methods primarily rely on shared users (overlapping users) to learn transferable interest representations. However, these approaches have limited information propagation, benefiting mainly overlapping users and those with rich interaction histories while neglecting non-overlapping (cold-start) and long-tailed users, who constitute the majority in real-world scenarios. To address this issue, we propose i$^2$VAE, a novel variational autoencoder (VAE)-based framework that enhances user interest learning with mutual information-based regularizers. i$^2$VAE improves recommendations for cold-start and long-tailed users while maintaining strong performance across all user groups. Specifically, cross-domain and disentangling regularizers extract transferable features for cold-start users, while a pseudo-sequence generator synthesizes interactions for long-tailed users, refined by a denoising regularizer to filter noise and preserve meaningful interest signals. Extensive experiments demonstrate that i$^2$VAE outperforms state-of-the-art methods, underscoring its effectiveness in real-world CDSR applications. Code and datasets are available at https://github.com/WujiangXu/IM-VAE.
APA
Ning, X., Xu, W., Wei, T. & Liu, X.. (2025). i$^2$VAE: Interest Information Augmentation with Variational Regularizers for Cross-Domain Sequential Recommendation. Proceedings of the Forty-first Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research 286:3235-3251 Available from https://proceedings.mlr.press/v286/ning25a.html.

Related Material