arXiv research

Proposes a GNN for multivariate time-series prediction with filtering.

New model predicts travel demand uncertainty with high accuracy.

A new method detects financial fraud using graph transformers.

Proposes a method to forecast spatial-temporal data with limited training data.

Video sequences contain rich dynamic patterns, such as dynamic texture patterns that exhibit stationarity in the temporal domain, and action patterns that are non-stationary in either spatial or temporal domain. We show that a spatial-temporal generative ConvNet can be used to model and synthesize dynamic patterns. The…

Diffusion Transformer captures spatial-temporal dependencies in sequential data.

Spatial-temporal prediction is a fundamental problem for constructing smart city, which is useful for tasks such as traffic control, taxi dispatching, and environmental policy making. Due to data collection mechanism, it is common to see data collection with unbalanced spatial distributions. For example, some cities ma…

Urban spatial-temporal flows prediction is of great importance to traffic management, land use, public safety, etc. Urban flows are affected by several complex and dynamic factors, such as patterns of human activities, weather, events and holidays. Datasets evaluated the flows come from various sources in different dom…

MIP framework improves urban flow prediction by adapting to distribution shifts.

STCA discovers dynamic functional brain networks using spatial-temporal convolution and attention.

Proposes a non-autoregressive Transformer for time series forecasting.

Deep learning has revolutionized many machine learning tasks in recent years, ranging from image classification and video processing to speech recognition and natural language understanding. The data in these tasks are typically represented in the Euclidean space. However, there is an increasing number of applications …

STOIC improves energy demand forecasting with reliable uncertainty estimates.

Understanding and accurately predicting within-field spatial variability of crop yield play a key role in site-specific management of crop inputs such as irrigation water and fertilizer for optimized crop production. However, such a task is challenged by the complex interaction between crop growth and environmental and…

The recent discovered spatial-temporal information processing capability of bio-inspired Spiking neural networks (SNN) has enabled some interesting models and applications. However designing large-scale and high-performance model is yet a challenge due to the lack of robust training algorithms. A bio-plausible SNN mode…

Mobile and ubiquitous sensing of urban air quality has received increased attention as an economically and operationally viable means to survey atmospheric environment with high spatial-temporal resolution. This paper proposes a machine learning based mobile air pollution sensing framework, called Deep-MAPS, and demons…

Proposes KStar Diffuser for kinematics-aware bimanual robotic manipulation.

The recognition of sign language is a challenging task with an important role in society to facilitate the communication of deaf persons. We propose a new approach of Spatial-Temporal Graph Convolutional Network to sign language recognition based on the human skeletal movements. The method uses graphs to capture the si…

Proposes a new model to predict travel demand with zero-inflated and long-tail characteristics.

Eigen-GNN enhances GNNs by preserving graph structures.

Dynamic model captures spatial, temporal, and spatiotemporal volatility effects.

SHAKE-GNN scales GNNs for large graphs with multi-scale representations.

GPT-GNN pre-trains GNNs on unlabeled graphs to improve downstream performance.

LC-GNN improves GNNs for node classification by incorporating label consistency.

New insights into GNN optimization reveal skip connections and depth accelerate training.

Survey on GNNs' power and limitations.

GNNs with random node initialization are shown to be universally expressive.

Unified framework for adaptive connection sampling in GNNs improves performance and robustness.

New algorithms reduce communication in GNN training.

Graph neural network (GNN), as a powerful representation learning model on graph data, attracts much attention across various disciplines. However, recent studies show that GNN is vulnerable to adversarial attacks. How to make GNN more robust? What are the key vulnerabilities in GNN? How to address the vulnerabilities …

ADMP-GNN dynamically adjusts message-passing layers for better graph learning performance.

Spatial-temporal graph modeling is an important task to analyze the spatial relations and temporal trends of components in a system. Existing approaches mostly capture the spatial dependency on a fixed graph structure, assuming that the underlying relation between entities is pre-determined. However, the explicit graph…

CI-GNN uses GNNs to diagnose psychiatric disorders by identifying causally relevant brain regions.

Graph neural networks (GNNs) are powerful machine learning models for various graph learning tasks. Recently, the limitations of the expressive power of various GNN models have been revealed. For example, GNNs cannot distinguish some non-isomorphic graphs and they cannot learn efficient graph algorithms. In this paper,…

Learning node embeddings that capture a node's position within the broader graph structure is crucial for many prediction tasks on graphs. However, existing Graph Neural Network (GNN) architectures have limited power in capturing the position/location of a given node with respect to all other nodes of the graph. Here w…

New BNN method reduces training time and model size.

Flow prediction (e.g., crowd flow, traffic flow) with features of spatial-temporal is increasingly investigated in AI research field. It is very challenging due to the complicated spatial dependencies between different locations and dynamic temporal dependencies among different time intervals. Although measurements of …

UM-GNN improves GNN robustness against poisoning attacks.

TF-GNN simplifies graph neural networks in TensorFlow.

Paper tackles fairness issues in GNNs by proposing ELEGANT for certification.

Paper improves generalization bounds for multi-kernel learning with mixed datasets.

DeepONets enhance spatial-temporal surrogates for structural dynamics.

Simplified NAS for GNN architectures improves efficiency and expressiveness.

A new method for training GNNs without a teacher model.

GNNs generalize CNNs for graph data, showing equivariance and stability.

Researchers explore statistical perspectives to understand GNN generalization.

Tail-GNNs improve protein function prediction using relational reinforcement.

GraphNorm accelerates GNN training by adapting InstanceNorm, improving convergence and generalization.