Abstract
Textual interaction networks (TINs) are an omnipresent data structure used to model the interplay between users and items on e-commerce websites, social networks, etc., where each interaction is associated with a text description. Classifying such textual interactions (TIC) finds extensive use in detecting spam reviews in e-commerce, fraudulent transactions in finance, and so on. Existing TIC solutions either (i) fail to capture the rich text semantics due to the use of context-free text embeddings, and/or (ii) disregard the bipartite structure and node heterogeneity of TINs, leading to compromised TIC performance. In this work, we propose SAFT, a new architecture that integrates language- and graph-based modules for the effective fusion of textual and structural semantics in the representation learning of interactions. In particular, line graph attention (LGA)/gated attention units (GAUs) and pretrained language models (PLMs) are capitalized on to model the interaction-level and token-level signals, which are further coupled via the proxy token in an iterative and contextualized fashion. Additionally, an efficient and theoretically-grounded approach is developed to encode the local and global topology information pertaining to interactions into structural embeddings. The resulting embeddings not only inject the structural features underlying TINs into the textual interaction encoding but also facilitate the design of graph sampling strategies. Extensive empirical evaluations on multiple real TIN datasets demonstrate the superiority of SAFT over the state-of-the-art baselines in TIC accuracy.
Original language | English |
---|---|
Title of host publication | Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2025 |
Publisher | Association for Computing Machinery (ACM) |
Number of pages | 14 |
Publication status | Published - 13 Jul 2025 |
Event | 48th International ACM SIGIR Conference on Research and Development in Information Retrieval - Padova Congress Center, Padua, Italy Duration: 13 Jul 2025 → 17 Jul 2025 https://sigir2025.dei.unipd.it/ (Conference website) https://sigir2025.dei.unipd.it/overall-program.html (Conference program) https://sigir2025.dei.unipd.it/accepted-papers.html (Accepted papers) |
Publication series
Name | Proceedings of the International ACM SIGIR Conference on Research and Development in Information Retrieval |
---|
Conference
Conference | 48th International ACM SIGIR Conference on Research and Development in Information Retrieval |
---|---|
Abbreviated title | ICTIR 2025 |
Country/Territory | Italy |
City | Padua |
Period | 13/07/25 → 17/07/25 |
Internet address |
|
User-Defined Keywords
- textual interaction
- Transformer
- message passing