cs.LGOct 29, 2025

Why Freeze the Encoder? A Controlled Study of End-to-End Sequence-Graph Learning for User Behavior

Authors: Yuen Chen, Yulun Wu, Samuel Sharpe, Igor Melnyk, Nam H. Nguyen, Furong Huang, C. Bayan Bruss, Rizal Fathony

Organizations: University of Illinois, Urbana-Champaign · Capital One · University of Maryland, College Park.

Abstract

Modeling user behavior couples two distinct signals: a per-user sequence of events and a persistent user-to-user relation graph. Standard pipelines preserve these native formats by combining them in two stages: a sequence encoder is pretrained, its per-user embeddings are frozen, and a graph model is trained on top to allow for cheap serving and cross-task reuse. We ask a simple question: does training the sequence and graph models end-to-end help, and if so, when? To isolate the impact of the training strategy, we hold a standard sequence-encoder-to-GNN pipeline fixed and vary only the optimization method; on Brightkite, a matched control that starts both pipelines from the same pretrained encoder and changes only whether it is updated attributes a 10.6-point MRR gain to end-to-end updating. Across relationship prediction and fraud detection on five real-world datasets, we find that the benefit of end-to-end training is conditional: it improves clearly over frozen two-stage pipelines on relationship prediction, where the relation graph appears to carry much of the signal, whereas gains shrink where the predictive signal is largely node-local (fraud detection), a regime in which a text-fed relational graph transformer achieves competitive results. Furthermore, recasting the data as a temporal graph yields inconsistent results compared to this native sequence-graph formulation. Ultimately, this work provides a controlled empirical account of when jointly training the two structures helps.

Figures & tables

Appendix figures & tables20 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Leveraging Graph Structure in Seq2Seq Models for Knowledge Graph Link Prediction

    May 18, 2026Luu Huu Phuc, Ratan Bahadur Thapa, Mojtaba Nayyeri +3Sequence ModelingKG Completion

  2. Bridging Semantics and Structure: A Theoretically Grounded Framework for Link Prediction on TAGs

    Oct 29, 2026Chen Shao, Ruirui Wang, Tobias Kafer +1Text-Attributed Graph LearningGraph Neural Networks

  3. Beyond Isolated Clients: Integrating Graph-Based Embeddings into Event Sequence Models

    Apr 10, 2026Harry Proshian, Nikita Severin, Sergey Nikolenko +5Self-Supervised LearningContrastive Learning