Skip to content

ReLaG: A Scalable Framework Generalizing Random Splits to Data with Latent Relations

Sep 2026 · arXiv.org · Vol abs/2609.38538 · 0 citations · 63 references
Computer Science

TL;DR

ReLaG is introduced, a modality-agnostic framework that models sample relatedness through a hierarchical latent-variable process and infers groups of related samples using proximity graphs and community detection to produce independent train--test subsets.

Abstract

Random splitting can yield non-independent train--test subsets when a dataset contains related samples, as is common in certain applications such as biochemical studies. This leads to overly optimistic generalization estimates. Here, we introduce ReLaG, a modality-agnostic framework that models sample relatedness through a hierarchical latent-variable process and infers groups of related samples using proximity graphs and community detection to produce independent train--test subsets. Across molecular and protein datasets, ReLaG matches existing relation-aware methods while scaling substantially better, enabling splits at previously impractical dataset sizes. We further introduce a label-free procedure that adapts the splitting resolution to production data, aligning evaluation with the intended deployment setting. ReLaG's inferred groups provide a cheap estimate of effective dataset size, enabling diversity-aware dataset scaling. ReLaG is open source and can be installed with pip install relag.

View source

Similar papers

#graph neural networks Open access Sep 2026

Feature-Refinement Classification Head (FCH) for Modeling Inter-Sample Relationships in Neural Networks

Conventional classification methods rely on the assumption that samples are independent and identically distributed, often ignoring the latent relational structures governing real-world data. Consequently, these methods fail to capture cross-sample dependencies, resulting in impoverished feature representations and sub...

Sooin Kim, Kyungtae Kim, Donghoon Kim et al. · 0 citations
#artificial intelligence Preprint Oct 2026

Scalable, Transferable Meta-network for Data Selection Requires a Different Loss (and Why the Obvious Choice is Problematic)

Data selection is critical for training large language models on massive and heterogeneous corpora. Meta-learning for Training-data Selection offers a principled alternative to heuristic scoring by learning data weights from a target validation objective, but existing methods face a trade-off between fine-grained valua...

Zi-Lin Du, Bo-Wen Yang, Bo-Yang Li · 1 citation
Preprint Nov 2026

ZIO: Order-Based Structure Learning for Zero-Inflated Count Data under Data Heterogeneity

We propose a structure learning method for directed acyclic graph (DAG) models of zero-inflated multivariate count data. Although causal structure learning with zero-inflated Poisson models is identifiable, existing algorithms rely on local search over the DAG space, leading to poor scalability and a tendency to conver...

Fariha Taskin, Junsouk Choi, Hyunwoong Chang · 0 citations
#machine learning Preprint Oct 2026

No-Free-Graph: Learning When Multimodal Data Should Be Graphified

Multimodal graph learning has recently emerged as an effective paradigm for in corporating inter-entity relationships into multimodal representations. Existing studies have made substantial progress on how to construct and optimize graphs, but rarely consider a more fundamental question: whether additional relational s...

Ze-Kai Chen, Kai Hu, Yu-Xin Zeng et al. · 0 citations

NodeGround: A Node Classification Benchmark in the Graph Foundation Model Era

Can a pretrained graph model replace training and tuning a separate predictor for each dataset? Answering this requires evaluating prediction quality alongside computational cost. We present NodeGround, a node classification benchmark that puts graph foundation models (GFMs) and dataset-specific supervised learning und...

Jin-Mo Lee, Dooho Lee, Minho Jeong et al. · 1 citation

Related blog posts

MIT News · Artificial Intelligence Sep 29, 2026

Who we become when we talk to machines

Professor Sherry Turkle’s new book, “Artificial Intimacy,” offers a withering critique of chatbots and the antisocial dynamics she believes they encourage.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.