English
Related papers

Related papers: Provably expressive temporal graph networks

200 papers

Most instruments - formalisms, concepts, and metrics - for social networks analysis fail to capture their dynamics. Typical systems exhibit different scales of dynamics, ranging from the fine-grain dynamics of interactions (which recently…

Social and Information Networks · Computer Science 2011-02-04 Nicola Santoro , Walter Quattrociocchi , Paola Flocchini , Arnaud Casteigts , Frederic Amblard

Temporal Graph Neural Networks (TGNNs) have emerged as powerful tools for modeling dynamic interactions across various domains. The design space of TGNNs is notably complex, given the unique challenges in runtime efficiency and scalability…

Machine Learning · Computer Science 2024-12-31 Yuxin Yang , Hongkuan Zhou , Rajgopal Kannan , Viktor Prasanna

With recent advances in sensing technologies, a myriad of spatio-temporal data has been generated and recorded in smart cities. Forecasting the evolution patterns of spatio-temporal data is an important yet demanding aspect of urban…

Machine Learning · Computer Science 2023-11-27 Guangyin Jin , Yuxuan Liang , Yuchen Fang , Zezhi Shao , Jincai Huang , Junbo Zhang , Yu Zheng

We propose a Graph Neural Network with greater expressive power than commonly used GNNs - not constrained to only differentiate between graphs that Weisfeiler-Lehman test recognizes to be non-isomorphic. We use a graph attention network…

Machine Learning · Computer Science 2020-04-14 Stanisław Purgał

Message passing graph neural networks (GNNs) are known to have their expressiveness upper-bounded by 1-dimensional Weisfeiler-Leman (1-WL) algorithm. To achieve more powerful GNNs, existing attempts either require ad hoc features, or…

Machine Learning · Computer Science 2024-01-24 Meng Liu , Haiyang Yu , Shuiwang Ji

Networks evolve continuously over time with the addition, deletion, and changing of links and nodes. Such temporal networks (or edge streams) consist of a sequence of timestamped edges and are seemingly ubiquitous. Despite the importance of…

Machine Learning · Computer Science 2020-07-20 John Boaz Lee , Giang Nguyen , Ryan A. Rossi , Nesreen K. Ahmed , Eunyee Koh , Sungchul Kim

Dynamic networks have intrinsic structural, computational, and multidisciplinary advantages. Link prediction estimates the next relationship in dynamic networks. However, in the current link prediction approaches, only bipartite or…

Social and Information Networks · Computer Science 2020-06-09 Mohamoud Ali , Yugyung Lee , Praveen Rao

Temporal Graph Neural Networks (TGNNs) are pivotal in processing dynamic graphs. However, existing TGNNs primarily target one-time predictions for a given temporal span, whereas many practical applications require continuous predictions,…

Machine Learning · Computer Science 2026-02-16 Zulun Zhu , Siqiang Luo

The pairwise interaction paradigm of graph machine learning has predominantly governed the modelling of relational systems. However, graphs alone cannot capture the multi-level interactions present in many complex systems and the expressive…

Machine Learning · Computer Science 2021-06-15 Cristian Bodnar , Fabrizio Frasca , Yu Guang Wang , Nina Otter , Guido Montúfar , Pietro Liò , Michael Bronstein

Graph neural networks (GNNs) are effective machine learning models for many graph-related applications. Despite their empirical success, many research efforts focus on the theoretical limitations of GNNs, i.e., the GNNs expressive power.…

Machine Learning · Computer Science 2025-01-13 Bingxu Zhang , Changjun Fan , Shixuan Liu , Kuihua Huang , Xiang Zhao , Jincai Huang , Zhong Liu

Comprehending the interplay between spatial and temporal characteristics of neural dynamics can contribute to our understanding of information processing in the human brain. Graph neural networks (GNNs) provide a new possibility to…

Neurons and Cognition · Quantitative Biology 2022-04-29 Simon Wein , Alina Schüller , Ana Maria Tomé , Wilhelm M. Malloni , Mark W. Greenlee , Elmar W. Lang

Temporal networks, i.e., networks in which the interactions among a set of elementary units change over time, can be modelled in terms of time-varying graphs, which are time-ordered sequences of graphs over a set of nodes. In such graphs,…

Physics and Society · Physics 2013-06-04 Vincenzo Nicosia , John Tang , Cecilia Mascolo , Mirco Musolesi , Giovanni Russo , Vito Latora

The effectiveness of Spatio-temporal Graph Neural Networks (STGNNs) in time-series applications is often limited by their dependence on fixed, hand-crafted input graph structures. Motivated by insights from the Topological Data Analysis…

Machine Learning · Computer Science 2025-03-20 Viet The Nguyen , Duy Anh Pham , An Thai Le , Jans Peter , Gunther Gust

Recurrent neural networks (RNNs) are powerful dynamical models, widely used in machine learning (ML) and neuroscience. Prior theoretical work has focused on RNNs with additive interactions. However, gating - i.e. multiplicative -…

Disordered Systems and Neural Networks · Physics 2021-12-02 Kamesh Krishnamurthy , Tankut Can , David J. Schwab

Graph generative models are highly important for sharing surrogate data and benchmarking purposes. Real-world complex systems often exhibit dynamic nature, where the interactions among nodes change over time in the form of a temporal…

Social and Information Networks · Computer Science 2023-06-21 Penghang Liu , A. Erdem Sarıyüce

Dynamic graph neural networks (DGNNs) that operate on snapshot sequences typically fall into one of two categories. \emph{Temporal-first} approaches build per-node temporal embeddings and only afterwards perform spatial aggregation, whereas…

Machine Learning · Computer Science 2026-05-26 Shubhajit Roy , Anirban Dasgupta

The event graph representation of temporal networks suggests that the connectivity of temporal structures can be mapped to a directed percolation problem. However, similar to percolation theory on static networks, this mapping is valid…

Physics and Society · Physics 2023-06-13 Arash Badie-Modiri , Abbas K. Rizi , Márton Karsai , Mikko Kivelä

Message passing Graph Neural Networks (GNNs) provide a powerful modeling framework for relational data. However, the expressive power of existing GNNs is upper-bounded by the 1-Weisfeiler-Lehman (1-WL) graph isomorphism test, which means…

Machine Learning · Computer Science 2021-02-08 Jiaxuan You , Jonathan Gomes-Selman , Rex Ying , Jure Leskovec

We perform the first adversarial robustness study into Graph Neural Networks (GNNs) that are provably more powerful than traditional Message Passing Neural Networks (MPNNs). In particular, we use adversarial robustness as a tool to uncover…

Machine Learning · Computer Science 2024-07-04 Francesco Campi , Lukas Gosch , Tom Wollschläger , Yan Scholten , Stephan Günnemann

Temporal graph representation learning has drawn significant attention for the prevalence of temporal graphs in the real world. However, most existing works resort to taking discrete snapshots of the temporal graph, or are not inductive to…

Social and Information Networks · Computer Science 2022-03-29 Zhihao Wen , Yuan Fang