21 citations · 47 across the 14 of their papers we have counts for
14 papers
Bridging Input Feature Spaces Towards Graph Foundation Models
Moshe Eliasof, Krishna Sri Ipsit Mantri, Beatrice Bevilacqua +2
Unlike vision and language domains, graph learning lacks a shared input space, as input features differ across graph datasets not only in semantics, but also in value ranges and di…
Boosting Relational Deep Learning with Pretrained Tabular Models
Veronica Lachi, Antonio Longa, Beatrice Bevilacqua +3
Relational databases, organized into tables connected by primary-foreign key relationships, are a common format for organizing data. Making predictions on relational data often inv…
TRIX: A More Expressive Model for Zero-shot Domain Transfer in Knowledge Graphs
Yucheng Zhang, Beatrice Bevilacqua, Mikhail Galkin +1
Fully inductive knowledge graph models can be trained on multiple domains and subsequently perform zero-shot knowledge graph completion (KGC) in new unseen domains. This is an impo…
On the Effectiveness of Random Weights in Graph Neural Networks
Thu Bui, Carola-Bibiane Schönlieb, Bruno Ribeiro +2
Graph Neural Networks (GNNs) have achieved remarkable success across diverse tasks on graph-structured data, primarily through the use of learned weights in message passing layers.…
DiGRAF: Diffeomorphic Graph-Adaptive Activation Function
Krishna Sri Ipsit Mantri, Xinzhi Wang, Carola-Bibiane Schönlieb +3
In this paper, we propose a novel activation function tailored specifically for graph data in Graph Neural Networks (GNNs). Motivated by the need for graph-adaptive and flexible ac…
GRANOLA: Adaptive Normalization for Graph Neural Networks
Moshe Eliasof, Beatrice Bevilacqua, Carola-Bibiane Schönlieb +1
In recent years, significant efforts have been made to refine the design of Graph Neural Network (GNN) layers, aiming to overcome diverse challenges, such as limited expressive pow…
Subgraphormer: Unifying Subgraph GNNs and Graph Transformers via Graph Products
Guy Bar-Shalom, Beatrice Bevilacqua, Haggai Maron
In the realm of Graph Neural Networks (GNNs), two exciting research directions have recently emerged: Subgraph GNNs and Graph Transformers. In this paper, we propose an architectur…
Efficient Subgraph GNNs by Learning Effective Selection Policies
Beatrice Bevilacqua, Moshe Eliasof, Eli Meirom +2
Subgraph GNNs are provably expressive neural architectures that learn graph representations from sets of subgraphs. Unfortunately, their applicability is hampered by the computatio…
A Multi-Task Perspective for Link Prediction with New Relation Types and Nodes
Jincheng Zhou, Beatrice Bevilacqua, Bruno Ribeiro
The task of inductive link prediction in (discrete) attributed multigraphs infers missing attributed links (relations) between nodes in new test multigraphs. Traditional relational…
Graph Positional Encoding via Random Feature Propagation
Moshe Eliasof, Fabrizio Frasca, Beatrice Bevilacqua +3
Two main families of node feature augmentation schemes have been explored for enhancing GNNs: random features and spectral positional encoding. Surprisingly, however, there is stil…
Causal Lifting and Link Prediction
Leonardo Cotta, Beatrice Bevilacqua, Nesreen Ahmed +1
Existing causal models for link prediction assume an underlying set of inherent node factors -- an innate characteristic defined at the node's birth -- that governs the causal evol…
Understanding and Extending Subgraph GNNs by Rethinking Their Symmetries
Fabrizio Frasca, Beatrice Bevilacqua, Michael M. Bronstein +1
Subgraph GNNs are a recent class of expressive Graph Neural Networks (GNNs) which model graphs as collections of subgraphs. So far, the design space of possible Subgraph GNN archit…
Equivariant Subgraph Aggregation Networks
Beatrice Bevilacqua, Fabrizio Frasca, Derek Lim +5
Message-passing neural networks (MPNNs) are the leading architecture for deep learning on graph-structured data, in large part due to their simplicity and scalability. Unfortunatel…
Size-Invariant Graph Representations for Graph Classification Extrapolations
Beatrice Bevilacqua, Yangze Zhou, Bruno Ribeiro
In general, graph representation learning methods assume that the train and test data come from the same distribution. In this work we consider an underexplored area of an otherwis…