Related papers: Heterogeneous relational message passing networks …

Heterogeneous information networks (HINs) are widely employed for describing real-world data with intricate entities and relationships. To automatically utilize their semantic information, graph neural architecture search has recently been…

Many real world systems need to operate on heterogeneous information networks that consist of numerous interacting components of different types. Examples include systems that perform data analysis on biological information networks; social…

While the celebrated graph neural networks yield effective representations for individual nodes of a graph, there has been relatively less success in extending to the task of graph similarity learning. Recent work on graph similarity…

Trajectory forecasting plays a pivotal role in the field of intelligent vehicles or social robots. Recent works focus on modeling spatial social impacts or temporal motion attentions, but neglect inherent properties of motions, i.e. moving…

Computational simulation of chemical and biological systems using ab initio molecular dynamics has been a challenge over decades. Researchers have attempted to address the problem with machine learning and fragmentation-based methods.…

In heterogeneous graphs, we can observe complex structures such as tree-like or hierarchical structures. Recently, the hyperbolic space has been widely adopted in many studies to effectively learn these complex structures. Although these…

We introduce the hyperedge event model (HEM)---a generative model for events that can be represented as directed edges with one sender and one or more receivers or one receiver and one or more senders. We integrate a dynamic version of the…

Model merging has emerged as a powerful paradigm for combining the capabilities of distinct expert models without the high computational cost of retraining, yet current methods are fundamentally constrained to homogeneous architectures. For…

Graph-level regression underpins many real-world applications, yet public benchmarks remain heavily skewed toward molecular graphs and citation networks. This limited diversity hinders progress on models that must generalize across both…

Message passing neural networks (MPNNs) have emerged as go-to models for learning on graph-structured data in the past decade. Despite their effectiveness, most of such models still incur severe issues such as over-smoothing and…

Network representation aims to represent the nodes in a network as continuous and compact vectors, and has attracted much attention in recent years due to its ability to capture complex structure relationships inside networks. However,…

Demystifying the interactions among multiple agents from their past trajectories is fundamental to precise and interpretable trajectory prediction. However, previous works only consider pair-wise interactions with limited relational…

Predicting the next interaction of a short-term interaction session is a challenging task in session-based recommendation. Almost all existing works rely on item transition patterns, and neglect the impact of user historical sessions while…

A common practice in heterogeneous graph neural networks (HGNNs) is to condition parameters on node/edge types, assuming types reflect semantic roles. However, this can cause overreliance on surface-level labels and impede cross-type…

We propose a friend recommendation system (an application of link prediction) using edge embeddings on social networks. Most real-world social networks are multi-graphs, where different kinds of relationships (e.g. chat, friendship) are…

We study collaborative machine learning (ML) across wireless devices, each with its own local dataset. Offloading these datasets to a cloud or an edge server to implement powerful ML solutions is often not feasible due to latency, bandwidth…

Graph neural networks (GNNs) have demonstrated significant promise in modelling relational data and have been widely applied in various fields of interest. The key mechanism behind GNNs is the so-called message passing where information is…

Accurate prediction of blood-brain barrier permeability (BBBP) is essential for central nervous system (CNS) drug development. While graph neural networks (GNNs) have advanced molecular property prediction, they often rely on molecular…

Hypergraphs are vital in modelling data with higher-order relations containing more than two entities, gaining prominence in machine learning and signal processing. Many hypergraph neural networks leverage message passing over hypergraph…

Graph kernels have recently emerged as a promising approach for tackling the graph similarity and learning tasks at the same time. In this paper, we propose a general framework for designing graph kernels. The proposed framework capitalizes…