High-Order Consistency-Guided User Identity Linkage with Large Language Model

Tianpeng Li, Xiangjun Pei, Yinghui Wang, Qiyao Peng, Wenjun Wang
Proceedings of the 17th Asian Conference on Machine Learning, PMLR 304:399-414, 2025.

Abstract

With the rapid expansion of the Internet, people commonly maintain multiple account identities across different online platforms, creating latent cross-network associations. User Identity Linkage (UIL), which seeks to identify and associate multiple accounts belonging to the same individual across platforms, has emerged as a vital research direction with broad applications in cross-platform recommendation, unified user profiling, and so on. However, existing methods face two major challenges in real-world environments: cross-platform feature heterogeneity and attribute-structure representation fusion. To address these challenges, this paper propose a Multi-View Feature High-Order Consistency-Guided User Identity Linkage method UIL-HC-MV. Our approach mitigates cross-network heterogeneity by deeply integrating multi-view features and mining consistency in shared thematic information among users and their relational networks. We decompose cross-platform feature heterogeneity into two subproblems: attribute heterogeneity and structural heterogeneity. We first fuse attribute and structural views by coupling nodes’ random-walk sequences with neighborhood sampling to jointly extract node attributes and topological context. We then employ a Large Language Model to capture deep semantic information and contextual relationships across multiple text segments, distilling unified themes or high-order community features from the combined attribute-structure representation. Finally, we fine-tune a BERT model on the extracted high-order information to reinforce feature consistency and enable transfer learning for improved generalization. Extensive comparative experiments on real-world datasets demonstrate significant performance improvements over existing mainstream methods, validating the effectiveness of high-order information in alleviating cross-network heterogeneity and confirm the contribution of each component within our deeply integrated multi-view feature learning framework.

Cite this Paper

BibTeX
@InProceedings{pmlr-v304-li25b, title = {High-Order Consistency-Guided User Identity Linkage with Large Language Model}, author = {Li, Tianpeng and Pei, Xiangjun and Wang, Yinghui and Peng, Qiyao and Wang, Wenjun}, booktitle = {Proceedings of the 17th Asian Conference on Machine Learning}, pages = {399--414}, year = {2025}, editor = {Lee, Hung-yi and Liu, Tongliang}, volume = {304}, series = {Proceedings of Machine Learning Research}, month = {09--12 Dec}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v304/main/assets/li25b/li25b.pdf}, url = {https://proceedings.mlr.press/v304/li25b.html}, abstract = {With the rapid expansion of the Internet, people commonly maintain multiple account identities across different online platforms, creating latent cross-network associations. User Identity Linkage (UIL), which seeks to identify and associate multiple accounts belonging to the same individual across platforms, has emerged as a vital research direction with broad applications in cross-platform recommendation, unified user profiling, and so on. However, existing methods face two major challenges in real-world environments: cross-platform feature heterogeneity and attribute-structure representation fusion. To address these challenges, this paper propose a Multi-View Feature High-Order Consistency-Guided User Identity Linkage method UIL-HC-MV. Our approach mitigates cross-network heterogeneity by deeply integrating multi-view features and mining consistency in shared thematic information among users and their relational networks. We decompose cross-platform feature heterogeneity into two subproblems: attribute heterogeneity and structural heterogeneity. We first fuse attribute and structural views by coupling nodes’ random-walk sequences with neighborhood sampling to jointly extract node attributes and topological context. We then employ a Large Language Model to capture deep semantic information and contextual relationships across multiple text segments, distilling unified themes or high-order community features from the combined attribute-structure representation. Finally, we fine-tune a BERT model on the extracted high-order information to reinforce feature consistency and enable transfer learning for improved generalization. Extensive comparative experiments on real-world datasets demonstrate significant performance improvements over existing mainstream methods, validating the effectiveness of high-order information in alleviating cross-network heterogeneity and confirm the contribution of each component within our deeply integrated multi-view feature learning framework.} }
Endnote
%0 Conference Paper %T High-Order Consistency-Guided User Identity Linkage with Large Language Model %A Tianpeng Li %A Xiangjun Pei %A Yinghui Wang %A Qiyao Peng %A Wenjun Wang %B Proceedings of the 17th Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Hung-yi Lee %E Tongliang Liu %F pmlr-v304-li25b %I PMLR %P 399--414 %U https://proceedings.mlr.press/v304/li25b.html %V 304 %X With the rapid expansion of the Internet, people commonly maintain multiple account identities across different online platforms, creating latent cross-network associations. User Identity Linkage (UIL), which seeks to identify and associate multiple accounts belonging to the same individual across platforms, has emerged as a vital research direction with broad applications in cross-platform recommendation, unified user profiling, and so on. However, existing methods face two major challenges in real-world environments: cross-platform feature heterogeneity and attribute-structure representation fusion. To address these challenges, this paper propose a Multi-View Feature High-Order Consistency-Guided User Identity Linkage method UIL-HC-MV. Our approach mitigates cross-network heterogeneity by deeply integrating multi-view features and mining consistency in shared thematic information among users and their relational networks. We decompose cross-platform feature heterogeneity into two subproblems: attribute heterogeneity and structural heterogeneity. We first fuse attribute and structural views by coupling nodes’ random-walk sequences with neighborhood sampling to jointly extract node attributes and topological context. We then employ a Large Language Model to capture deep semantic information and contextual relationships across multiple text segments, distilling unified themes or high-order community features from the combined attribute-structure representation. Finally, we fine-tune a BERT model on the extracted high-order information to reinforce feature consistency and enable transfer learning for improved generalization. Extensive comparative experiments on real-world datasets demonstrate significant performance improvements over existing mainstream methods, validating the effectiveness of high-order information in alleviating cross-network heterogeneity and confirm the contribution of each component within our deeply integrated multi-view feature learning framework.
APA
Li, T., Pei, X., Wang, Y., Peng, Q. & Wang, W.. (2025). High-Order Consistency-Guided User Identity Linkage with Large Language Model. Proceedings of the 17th Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 304:399-414 Available from https://proceedings.mlr.press/v304/li25b.html.

Related Material