arXiv subjects

Charilaos Kanatsoulis

Publications and source records attributed to Charilaos Kanatsoulis.

10 recordsLinked to original sources

arXiv2026

RT-J: Large-Scale Pretraining of Relational Transformers for Context-Efficient Predictions

Foundation models for tables and relational databases are increasingly used for predictive tasks across various scientific and industrial domains. However, adapting existing models to unseen datasets requires tens of thousands of examples. Here we introduce RT-J, an 86M-parameter relational foundation model (RFM) that makes accurate predictions even with hundreds of in-context examples or fewer. To achieve this, we first assemble the Join, a large collection of 639 web-crawled databases with 6,023 LLM-generated forecasting tasks. We pretrain with long contexts of up to 8,192 database cells, using in-context examples from a novel lightweight random-walk retriever. Finally, we leverage context tuning and ensembling to scale up test-time compute. On in-context regression tasks from RelBench, RT-J requires 10x fewer examples on average to match strong feature engineering pipelines with LLM-agent or RDBLearn featurizers and TabICLv2 or LightGBM predictors. Overall, our work pushes the frontier for context-efficient predictions on relational data and highlights the importance of real-world semantics, context engineering and large-scale pretraining for RFMs.

cs.LG↗

arXiv2026

Graph Convolutional Attention: A Spectral Perspective on Graph Denoising and Diffusion

Denoising graphs is a fundamental problem in graph learning and the core operation of graph diffusion models. Attention-based architectures such as graph transformers have shown promise for this task, yet the mechanisms through which attention denoises graphs remain poorly understood. We show that, under a graph denoising objective, standard attention scores learn an average spectral denoising filter across the training distribution and are suboptimal when the graph spectra vary. To address this limitation, we introduce spectral attention scores, which are attention scores that depend on the input graph spectrum. We characterize the improvement over standard attention scores in terms of the spectral diversity of the graph distribution. We then propose graph convolutional attention (GCA), a practical realization of spectral attention that uses graph-filtered queries and keys. For asymptotically large stochastic block models, we show that GCA matches the optimal denoising loss of spectral attention under suitable conditions. We also show that softmax can further reduce denoising error by approximately projecting noisy eigenvectors onto the clean eigenspace. Across synthetic and real datasets, replacing standard query--key projections with GCA improves graph denoising and diffusion, with denoising gains correlated with spectral diversity. Furthermore, replacing the DiGress architecture with a GCA-based architecture within the DiGress generative framework yields comparable generation quality with significantly faster inference.

cs.LG↗

arXiv2026

RelBench v2: A Large-Scale Benchmark and Repository for Relational Data

Relational deep learning (RDL) has emerged as a powerful paradigm for learning directly on relational databases by modeling entities and their relationships across multiple interconnected tables. As this paradigm evolves toward larger models and relational foundation models, scalable and realistic benchmarks are essential for enabling systematic evaluation and progress. In this paper, we introduce RelBench v2, a major expansion of the RelBench benchmark for RDL. RelBench v2 adds four large-scale relational datasets spanning scholarly publications, enterprise resource planning, consumer platforms, and clinical records, increasing the benchmark to 11 datasets comprising over 22 million rows across 29 tables. We further introduce autocomplete tasks, a new class of predictive objectives that require models to infer missing attribute values directly within relational tables while respecting temporal constraints, expanding beyond traditional forecasting tasks constructed via SQL queries. In addition, RelBench v2 expands beyond its native datasets by integrating external benchmarks and evaluation frameworks: we translate event streams from the Temporal Graph Benchmark into relational schemas for unified relational-temporal evaluation, interface with ReDeLEx to provide uniform access to 70+ real-world databases suitable for pretraining, and incorporate 4DBInfer datasets and tasks to broaden multi-table prediction coverage. Experimental results demonstrate that RDL models consistently outperform single-table baselines across autocomplete, forecasting, and recommendation tasks, highlighting the importance of modeling relational structure explicitly.

cs.LG↗

arXiv2026

Relational Transformer: Toward Zero-Shot Foundation Models for Relational Data

Pretrained transformers readily adapt to new sequence modeling tasks via zero-shot prompting, but relational domains still lack architectures that transfer across datasets and tasks. The core challenge is the diversity of relational data, with varying heterogeneous schemas, graph structures and functional dependencies. In this paper, we present the Relational Transformer (RT) architecture, which can be pretrained on diverse relational databases and directly applied to unseen datasets and tasks without task- or dataset-specific fine-tuning, or retrieval of in-context examples. RT (i) incorporates task specification via task table prompting, (ii) tokenizes cells with table/column metadata, (iii) is pretrained via masked token prediction, and (iv) utilizes a novel Relational Attention mechanism over columns, rows, and primary-foreign key links. Pretrained on RelBench datasets spanning tasks such as churn and sales forecasting, RT attains strong zero-shot performance, averaging 93% of fully supervised AUROC on binary classification tasks with a single forward pass of a 22M parameter model, as opposed to 84% for a 27B LLM. Fine-tuning yields state-of-the-art results with high sample efficiency. Our experimental analyses show that RT's zero-shot transfer leverages task context, relational attention patterns and schema semantics. Overall, RT provides a practical path toward foundation models for relational data. Code, models, data: https://github.com/snap-stanford/relational-transformer.

cs.LG↗

arXiv2025

KGGen: Extracting Knowledge Graphs from Plain Text with Language Models

Recent interest in building foundation models for KGs has highlighted a fundamental challenge: knowledge-graph data is relatively scarce. The best-known KGs are primarily human-labeled, created by pattern-matching, or extracted using early NLP techniques. While human-generated KGs are in short supply, automatically extracted KGs are of questionable quality. We present a solution to this data scarcity problem in the form of a text-to-KG generator (KGGen), a package that uses language models to create high-quality graphs from plaintext. Unlike other KG extractors, KGGen clusters related entities to reduce sparsity in extracted KGs. KGGen is available as a Python library (\texttt{pip install kg-gen}), making it accessible to everyone. Along with KGGen, we release the first benchmark, Measure of of Information in Nodes and Edges (MINE), that tests an extractor's ability to produce a useful KG from plain text. We benchmark our new tool against existing extractors and demonstrate far superior performance.

cs.CL↗

arXiv2025

WindMiL: Equivariant Graph Learning for Wind Loading Prediction

Accurate prediction of wind loading on buildings is crucial for structural safety and sustainable design, yet conventional approaches such as wind tunnel testing and large-eddy simulation (LES) are prohibitively expensive for large-scale exploration. Each LES case typically requires at least 24 hours of computation, making comprehensive parametric studies infeasible. We introduce WindMiL, a new machine learning framework that combines systematic dataset generation with symmetry-aware graph neural networks (GNNs). First, we introduce a large-scale dataset of wind loads on low-rise buildings by applying signed distance function interpolation to roof geometries and simulating 462 cases with LES across varying shapes and wind directions. Second, we develop a reflection-equivariant GNN that guarantees physically consistent predictions under mirrored geometries. Across interpolation and extrapolation evaluations, WindMiL achieves high accuracy for both the mean and the standard deviation of surface pressure coefficients (e.g., RMSE $\leq 0.02$ for mean $C_p$) and remains accurate under reflected-test evaluation, maintaining hit rates above $96\%$ where the non-equivariant baseline model drops by more than $10\%$. By pairing a systematic dataset with an equivariant surrogate, WindMiL enables efficient, scalable, and accurate predictions of wind loads on buildings.

cs.LG↗

arXiv2025

Relational Deep Learning: Challenges, Foundations and Next-Generation Architectures

Graph machine learning has led to a significant increase in the capabilities of models that learn on arbitrary graph-structured data and has been applied to molecules, social networks, recommendation systems, and transportation, among other domains. Data in multi-tabular relational databases can also be constructed as 'relational entity graphs' for Relational Deep Learning (RDL) - a new blueprint that enables end-to-end representation learning without traditional feature engineering. Compared to arbitrary graph-structured data, relational entity graphs have key properties: (i) their structure is defined by primary-foreign key relationships between entities in different tables, (ii) the structural connectivity is a function of the relational schema defining a database, and (iii) the graph connectivity is temporal and heterogeneous in nature. In this paper, we provide a comprehensive review of RDL by first introducing the representation of relational databases as relational entity graphs, and then reviewing public benchmark datasets that have been used to develop and evaluate recent GNN-based RDL models. We discuss key challenges including large-scale multi-table integration and the complexities of modeling temporal dynamics and heterogeneous data, while also surveying foundational neural network methods and recent architectural advances specialized for relational entity graphs. Finally, we explore opportunities to unify these distinct modeling challenges, highlighting how RDL converges multiple sub-fields in graph machine learning towards the design of foundation models that can transform the processing of relational data.

cs.LG↗

arXiv2025

RelGNN: Composite Message Passing for Relational Deep Learning

Predictive tasks on relational databases are critical in real-world applications spanning e-commerce, healthcare, and social media. To address these tasks effectively, Relational Deep Learning (RDL) encodes relational data as graphs, enabling Graph Neural Networks (GNNs) to exploit relational structures for improved predictions. However, existing RDL methods often overlook the intrinsic structural properties of the graphs built from relational databases, leading to modeling inefficiencies, particularly in handling many-to-many relationships. Here we introduce RelGNN, a novel GNN framework specifically designed to leverage the unique structural characteristics of the graphs built from relational databases. At the core of our approach is the introduction of atomic routes, which are simple paths that enable direct single-hop interactions between the source and destination nodes. Building upon these atomic routes, RelGNN designs new composite message passing and graph attention mechanisms that reduce redundancy, highlight key signals, and enhance predictive accuracy. RelGNN is evaluated on 30 diverse real-world tasks from Relbench (Fey et al., 2024), and achieves state-of-the-art performance on the vast majority of tasks, with improvements of up to 25%. Code is available at https://github.com/snap-stanford/RelGNN.

cs.LG↗

arXiv2025

LoRTA: Low Rank Tensor Adaptation of Large Language Models

Low Rank Adaptation (LoRA) is a popular Parameter Efficient Fine Tuning (PEFT) method that effectively adapts large pre-trained models for downstream tasks. LoRA parameterizes model updates using low-rank matrices at each layer, significantly reducing the number of trainable parameters and, consequently, resource requirements during fine-tuning. However, the lower bound on the number of trainable parameters remains high due to the use of the low-rank matrix model. Recent works have addressed this limitation by proposing low rank tensor parameterizations for model updates. However, they only exploit redundancy across layers, or tensorize individual matrices using ad-hoc schemes that introduce additional hyperparameters. In this work, we propose a higher-order Candecomp/Parafac (CP) decomposition, enabling a more compact and flexible representation compared to existing matrix and tensor based PEFT methods. Our experiments on Natural Language Understanding, Instruction Tuning, Preference Optimization and Protein Folding benchmarks demonstrate that our method can achieve a reduction in the number of parameters while maintaining comparable performance.

cs.CL↗

arXiv2022

Space-Time Graph Neural Networks with Stochastic Graph Perturbations

Space-time graph neural networks (ST-GNNs) are recently developed architectures that learn efficient graph representations of time-varying data. ST-GNNs are particularly useful in multi-agent systems, due to their stability properties and their ability to respect communication delays between the agents. In this paper we revisit the stability properties of ST-GNNs and prove that they are stable to stochastic graph perturbations. Our analysis suggests that ST-GNNs are suitable for transfer learning on time-varying graphs and enables the design of generalized convolutional architectures that jointly process time-varying graphs and time-varying signals. Numerical experiments on decentralized control systems validate our theoretical results and showcase the benefits of traditional and generalized ST-GNN architectures.

cs.LG↗