Pytorch frame: A modular framework for multi-modal tabular learning

W Hu, Y Yuan, Z Zhang, A Nitta, K Cao… - arxiv preprint arxiv …, 2024‏ - arxiv.org
We present PyTorch Frame, a PyTorch-based framework for deep learning over multi-modal
tabular data. PyTorch Frame makes tabular deep learning easy by providing a PyTorch …

CARTE: pretraining and transfer for tabular learning

MJ Kim, L Grinsztajn, G Varoquaux - arxiv preprint arxiv:2402.16785, 2024‏ - arxiv.org
Pretrained deep-learning models are the go-to solution for images or text. However, for
tabular data the standard is still to train tree-based models. Indeed, transfer learning on …

Anygraph: Graph foundation model in the wild

L **a, C Huang - 2024‏ - openreview.net
The growing ubiquity of relational data structured as graphs has underscored the need for
graph learning models with exceptional generalization capabilities. However, current …

Towards graph foundation models for personalization

A Damianou, F Fabbri, P Gigioli, M De Nadai… - … Proceedings of the …, 2024‏ - dl.acm.org
In the realm of personalization, integrating diverse information sources such as consumption
signals and content-based representations is becoming increasingly critical to build state-of …

Automating Feature Extraction from Entity-Relation Models: Experimental Evaluation of Machine Learning Methods for Relational Learning

B Stanoev, G Mitrov, A Kulakov, G Mirceva… - Big Data and Cognitive …, 2024‏ - mdpi.com
With the exponential growth of data, extracting actionable insights becomes resource-
intensive. In many organizations, normalized relational databases store a significant portion …

Revisiting Data Analysis with Pre-trained Foundation Models

C Liang, D Yang, Z Liang, Z Liang, T Zhang… - arxiv preprint arxiv …, 2025‏ - arxiv.org
Data analysis focuses on harnessing advanced statistics, programming, and machine
learning techniques to extract valuable insights from vast datasets. An increasing volume …

Learning Efficient Positional Encodings with Graph Neural Networks

CI Kanatsoulis, E Choi, S Jegelka, J Leskovec… - arxiv preprint arxiv …, 2025‏ - arxiv.org
Positional encodings (PEs) are essential for effective graph representation learning because
they provide position awareness in inherently position-agnostic transformer architectures …

ContextGNN: Beyond Two-Tower Recommendation Systems

Y Yuan, Z Zhang, X He, A Nitta, W Hu, D Wang… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Recommendation systems predominantly utilize two-tower architectures, which evaluate
user-item rankings through the inner product of their respective embeddings. However, one …

Hypergraph Neural Networks with Logic Clauses

JP Gandarela de Souza, G Zaverucha… - … Joint Conference on …, 2024‏ - openaccess.city.ac.uk
The analysis of structure in complex datasets has become essential to solving difficult
Machine Learning problems. Relational aspects of data, capturing relationships between …

TabGraphs: A Benchmark and Strong Baselines for Learning on Graphs with Tabular Node Features

G Bazhenov, O Platonov, L Prokhorenkova - arxiv preprint arxiv …, 2024‏ - arxiv.org
Tabular machine learning is an important field for industry and science. In this field, table
rows are usually treated as independent data samples, but additional information about …