Context Window Failures in Relational Foundation Models
Mirrored from arXiv — Machine Learning for archival readability. Support the source by reading on the original site.
Computer Science > Machine Learning
Title:Context Window Failures in Relational Foundation Models
Abstract:Recent Relational Deep Learning architectures have been proposed as foundation models for multi-table relational data, yet they impose constrained neighborhood budgets that force row truncation when an entity has many related records. We introduce Animus, a synthetic financial dataset in which predicting customer income requires aggregating up to tens of thousands of transactions. On the raw representation, three recently proposed models (RT, Griffin, RelGT) achieve $R^2 \le 0.18$; a single, routine, temporal pre-aggregation step recovers $R^2$ up to $0.65$. This questions whether current relational foundation models are ready for high-cardinality real-world data.
| Comments: | Accepted at the 2nd Foundation Models for Structured Data Workshop at ICML 2026, Seoul, South Korea. OpenReview: this https URL |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2609.00460 [cs.LG] |
| (or arXiv:2609.00460v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2609.00460
arXiv-issued DOI via DataCite (pending registration)
|
Submission history
From: Francisco Galuppo Azevedo [view email][v1] Mon, 31 Aug 2026 22:59:57 UTC (44 KB)
Access Paper:
- View PDF
- HTML (experimental)
- TeX Source
References & Citations
Bookmark
Bibliographic and Citation Tools
Code, Data and Media Associated with this Article
Demos
Recommenders and Search Tools
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
More from arXiv — Machine Learning
-
M3-Former: Multimodal Transformer with Mixture-of-Experts for Long-Term Vessel Trajectory Prediction
Sep 11
-
Halo: Improving forecast accuracy through heteroscedastic estimation
Sep 11
-
Zero-shot rib design: merging training-free generative prior with topology optimization
Sep 11
-
Byzantine-Robust Federated Fire Detection with a Rotating Coordinator
Sep 11
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.