241 citations · 399 across the 23 of their papers we have counts for
27 papers
RT-J: Large-Scale Pretraining of Relational Transformers for Context-Efficient Predictions
Rishabh Ranjan, Vignesh Kothapalli, Harshvardhan Agarwal +5
Foundation models for tables and relational databases are increasingly used for predictive tasks across various scientific and industrial domains. However, adapting existing models…
Graph Convolutional Attention: A Spectral Perspective on Graph Denoising and Diffusion
Shervin Khalafi, Igor Krawczuk, Sergio Rozada +3
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 pr…
RelBench v2: A Large-Scale Benchmark and Repository for Relational Data
Justin Gu, Rishabh Ranjan, Charilaos Kanatsoulis +8
Relational deep learning (RDL) has emerged as a powerful paradigm for learning directly on relational databases by modeling entities and their relationships across multiple interco…
Graph Learning Should Move Beyond Restrictive Views of Spectral and Message-Passing GNNs
Antonis Vasileiou, Juan Cervino, Pascal Frossard +7
Graph neural networks (GNNs) are commonly divided into message-passing neural networks (MPNNs) and spectral GNNs, reflecting two largely separate research traditions in machine lea…
WindMiL: Equivariant Graph Learning for Wind Loading Prediction
Themistoklis Vargiemezis, Charilaos Kanatsoulis, Catherine Gorlé
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 sim…
Relational Transformer: Toward Zero-Shot Foundation Models for Relational Data
Rishabh Ranjan, Valter Hudovernik, Mark Znidar +7
Pretrained transformers readily adapt to new sequence modeling tasks via zero-shot prompting, but relational domains still lack architectures that transfer across datasets and task…
Relational Deep Learning: Challenges, Foundations and Next-Generation Architectures
Vijay Prakash Dwivedi, Charilaos Kanatsoulis, Shenyang Huang +1
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 netwo…
Relational Graph Transformer
Vijay Prakash Dwivedi, Sri Jaladi, Yangyi Shen +5
Relational Deep Learning (RDL) is a promising approach for building state-of-the-art predictive models on multi-table relational data by representing it as a heterogeneous temporal…
Learning Efficient Positional Encodings with Graph Neural Networks
Charilaos I. Kanatsoulis, Evelyn Choi, Stephanie Jegelka +2
Positional encodings (PEs) are essential for effective graph representation learning because they provide position awareness in inherently position-agnostic transformer architectur…
KGGen: Extracting Knowledge Graphs from Plain Text with Language Models
Belinda Mo, Kyssen Yu, Joshua Kazdan +6
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-lab…
RelGNN: Composite Message Passing for Relational Deep Learning
Tianlang Chen, Charilaos Kanatsoulis, Jure Leskovec
Predictive tasks on relational databases are critical in real-world applications spanning e-commerce, healthcare, and social media. To address these tasks effectively, Relational D…
LoRTA: Low Rank Tensor Adaptation of Large Language Models
Ignacio Hounie, Charilaos Kanatsoulis, Arnuv Tandon +1
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 mode…
Generalizability of Graph Neural Networks for Decentralized Unlabeled Motion Planning
Shreyas Muthusamy, Damian Owerko, Charilaos I. Kanatsoulis +2
Unlabeled motion planning involves assigning a set of robots to target locations while ensuring collision avoidance, aiming to minimize the total distance traveled. The problem for…
T-GAE: Transferable Graph Autoencoder for Network Alignment
Jiashu He, Charilaos I. Kanatsoulis, Alejandro Ribeiro
Network alignment is the task of establishing one-to-one correspondences between the nodes of different graphs. Although finding a plethora of applications in high-impact domains,…
Transferability of Convolutional Neural Networks in Stationary Learning Tasks
Damian Owerko, Charilaos I. Kanatsoulis, Jennifer Bondarchuk +2
Recent advances in hardware and big data acquisition have accelerated the development of deep learning techniques. For an extended period of time, increasing the model complexity h…
Solving Large-scale Spatial Problems with Convolutional Neural Networks
Damian Owerko, Charilaos I. Kanatsoulis, Alejandro Ribeiro
Over the past decade, deep learning research has been accelerated by increasingly powerful hardware, which facilitated rapid growth in the model complexity and the amount of data i…
Space-Time Graph Neural Networks with Stochastic Graph Perturbations
Samar Hadou, Charilaos Kanatsoulis, Alejandro Ribeiro
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-Target Tracking with Transferable Convolutional Neural Networks
Damian Owerko, Charilaos I. Kanatsoulis, Jennifer Bondarchuk +2
Multi-target tracking (MTT) is a classical signal processing task, where the goal is to estimate the states of an unknown number of moving targets from noisy sensor measurements. I…
Representation Power of Graph Neural Networks: Improved Expressivity via Algebraic Analysis
Charilaos I. Kanatsoulis, Alejandro Ribeiro
Despite the remarkable success of Graph Neural Networks (GNNs), the common belief is that their representation power is limited and that they are at most as expressive as the Weisf…
Space-Time Graph Neural Networks
Samar Hadou, Charilaos I. Kanatsoulis, Alejandro Ribeiro
We introduce space-time graph neural network (ST-GNN), a novel GNN architecture, tailored to jointly process the underlying space-time topology of time-varying network data. The co…
GAGE: Geometry Preserving Attributed Graph Embeddings
Charilaos I. Kanatsoulis, Nicholas D. Sidiropoulos
Node embedding is the task of extracting concise and informative representations of certain entities that are connected in a network. Various real-world networks include informatio…
TeX-Graph: Coupled tensor-matrix knowledge-graph embedding for COVID-19 drug repurposing
Charilaos I. Kanatsoulis, Nicholas D. Sidiropoulos
Knowledge graphs (KGs) are powerful tools that codify relational behaviour between entities in knowledge bases. KGs can simultaneously model many different types of subject-predica…
Generalized Canonical Correlation Analysis: A Subspace Intersection Approach
Mikael Sørensen, Charilaos I. Kanatsoulis, Nicholas D. Sidiropoulos
Generalized Canonical Correlation Analysis (GCCA) is an important tool that finds numerous applications in data mining, machine learning, and artificial intelligence. It aims at fi…
PREMA: Principled Tensor Data Recovery from Multiple Aggregated Views
Faisal M. Almutairi, Charilaos I. Kanatsoulis, Nicholas D. Sidiropoulos
Multidimensional data have become ubiquitous and are frequently encountered in situations where the information is aggregated over multiple data atoms. The aggregation can be over…