This paper models the changes in graph adjacency matrices over time as a low-rank matrix and develops a method for jointly interpolating signals and estimating graph adjacency matrices using this assu…

The paper proposes Dual-Scale Retentive Dynamics (DSRD), a unified framework that improves representation learning on dynamic graphs by jointly modeling evolving temporal and structural dependencies.

The paper proposes GC-MoE, a graph-conditioned Mixture of Experts framework, to improve traffic forecasting by assigning personalized, specialized forecasting experts to individual road segments.

The paper proposes NLBST, a hierarchical Bayesian framework for continuous spatio-temporal fields with nonlocal interactions, enabling tractable inference and uncertainty quantification.

This paper proposes STOIC, a framework that integrates graph-based forecasting with tabular foundation models for uncertainty quantification in energy demand forecasting using spatial-temporal graph n…

This paper proposes SG-JEPA, a method for learning predictive embeddings for large-scale dynamic graphs by partitioning nodes into context and target sets and encoding sequential inputs into spike cou…

The paper introduces MeRa, a metric-space bias module, demonstrating that latent reasoning only improves spatial prediction when it is explicitly grounded in the underlying metric space.

This paper proposes a Meta-Role Temporal Graph Network (MR-TGN) framework for collective intent prediction in multi-agent systems, modeling agents as dynamically evolving graph entities and employing…

MORPHOS is a novel autoregressive framework that generates dynamic 3D assets (like meshes and radiance fields) from videos by using a unified 4D representation to ensure temporal consistency and handl…

Taurus is a single-machine system for efficient Graph Neural Network (GNN) inference on large-scale graphs that do not fit in RAM, using source-centric broadcasts and a pipelined GPU-CPU-SSD hierarchy…

This paper proposes a scalable topological learning framework for higher-order graph representation by introducing simplified and factored cellular Weisfeiler Leman tests and a novel random walk metho…

This paper investigates the effects of structural and temporal inhomogeneities in decentralised federated learning and shows that they significantly slow down the convergence process.

The paper introduces GraphARC, a new benchmark for abstract reasoning on graph-structured data, demonstrating that current state-of-the-art language models struggle with full graph transformation task…

This paper proposes Spiking Fourier Graph Operators (SpikF-GO) for multivariate time series forecasting using Spiking Neural Networks (SNNs), introducing Hard Concrete frequency gates and Complex LIF…

The paper introduces a hybrid WGAN-GA framework that uses a Genetic Algorithm (GA) to refine graphs generated by a GAN, significantly reducing structural deviations and improving realism.

The paper proposes a method for online novel view synthesis from multi-view streaming videos, decoupling memory update and application frequencies, using cross-view attention, Memory Loss, and Memory…