Graph Representational Learning: When Does More Expressivity Hurt Generalization?

HARMONIA: Interpretable Graph Learning through Mixtures of Neural Bases

HARMONIA achieves stronger explanation recovery than existing interpretable graph baselines while maintaining competitive predictive performance and scaling to graphs with millions of nodes, and shows that interpretable graph learning can remain both faithful and scalable without sacrificing predictive effectiveness.

Even-if Explanations for Graph Neural Networks

Transferable Graph Metanetworks

A weight space network (or metanetwork) takes the weights of another neural network as input and predicts properties of it. Most prior work trains such models on input networks of one or a few fixed sizes and evaluates them in-distribution. The few attempts at out-of-distribution size generalization remain limited in s...

Message Passing Does More with Less for In-Context Learning on Graphs

Achieving strong performance with graph neural networks (GNNs) typically requires training and hyperparameter tuning for each dataset, incurring repeated costs and effort. Graph in-context learning (ICL) avoids this by using a single pretrained model to predict unknown node labels directly from labeled context nodes. E...

Enhancing Knowledge Graph Embedding's via Logic Regularized Graph Neural Networks

In (high)-dimensional data, deep learning-based Knowledge Graph Embedding (KGE) models have shown better capacity in learning the true pattern of latent features. However, they are typically used as "black boxes", where statistical correlation is preferred over explicit logical inference. These are geometrically feasib...

Graph Additive Models disentangling feature, topology, and interactions

Graph Neural Additive Networks (GNANs) have emerged as effective, interpretable-by-design architectures for graph learning. They achieve transparency by combining per-feature shape functions with simple distance-based reweighting. However, GNANs have three limitations. First, node-wise relevance scores aggregate inform...