Related papers: How to Bridge Spatial and Temporal Heterogeneity i…
Learning on temporal graphs has become a central topic in graph representation learning, with numerous benchmarks indicating the strong performance of state-of-the-art models. However, recent work has raised concerns about the reliability…
Multi-person motion prediction is a complex and emerging field with significant real-world applications. Current state-of-the-art methods typically adopt dual-path networks to separately modeling spatial features and temporal features.…
Spatial-temporal graph representations play a crucial role in urban sensing applications, including traffic analysis, human mobility behavior modeling, and citywide crime prediction. However, a key challenge lies in the noisy and sparse…
Predicting traffic conditions has been recently explored as a way to relieve traffic congestion. Several pioneering approaches have been proposed based on traffic observations of the target location as well as its adjacent regions, but they…
Self-supervised contrastive learning is an effective approach for addressing the challenge of limited labelled data. This study builds upon the previously established two-stage patch-level, multi-label classification method for…
Heterogeneous graph neural networks (HGNNs) as an emerging technique have shown superior capacity of dealing with heterogeneous information network (HIN). However, most HGNNs follow a semi-supervised learning manner, which notably limits…
Multivariate time series anomaly detection technology plays an important role in many fields including aerospace, water treatment, cloud service providers, etc. Excellent anomaly detection models can greatly improve work efficiency and…
Telecommunication networks play a critical role in modern society. With the arrival of 5G networks, these systems are becoming even more diversified, integrated, and intelligent. Traffic forecasting is one of the key components in such a…
Representation learning methods for heterogeneous networks produce a low-dimensional vector embedding for each node that is typically fixed for all tasks involving the node. Many of the existing methods focus on obtaining a static vector…
Real-world networks and knowledge graphs are usually heterogeneous networks. Representation learning on heterogeneous networks is not only a popular but a pragmatic research field. The main challenge comes from the heterogeneity -- the…
Self-supervised learning (SSL) approaches have brought tremendous success across many tasks and domains. It has been argued that these successes can be attributed to a link between SSL and identifiable representation learning: Temporal…
Video self-supervised learning is a challenging task, which requires significant expressive power from the model to leverage rich spatial-temporal knowledge and generate effective supervisory signals from large amounts of unlabeled videos.…
We address the problem of predicting spatio-temporal processes with temporal patterns that vary across spatial regions, when data is obtained as a stream. That is, when the training dataset is augmented sequentially. Specifically, we…
Self-supervised learning (especially contrastive learning) methods on heterogeneous graphs can effectively get rid of the dependence on supervisory data. Meanwhile, most existing representation learning methods embed the heterogeneous…
Spatio-temporal prediction plays an important role in many application areas especially in traffic domain. However, due to complicated spatio-temporal dependency and high non-linear dynamics in road networks, traffic prediction task is…
The quality of data representation in deep learning methods is directly related to the prior model imposed on the representations; however, generally used fixed priors are not capable of adjusting to the context in the data. To address this…
Spatial networks, in which nodes and edges are embedded in space, play a vital role in the study of complex systems. For example, many social networks attach geo-location information to each user, allowing the study of not only topological…
Spiking Neural Networks (SNNs) are considered naturally suited for temporal processing, with membrane potential propagation widely regarded as the core temporal modeling mechanism. However, existing research lack analysis of its actual…
Heterogeneous networks are widely used to model real-world semi-structured data. The key challenge of learning over such networks is the modeling of node similarity under both network structures and contents. To deal with network…
Time-to-Collision (TTC) forecasting is a critical task in collision prevention, requiring precise temporal prediction and comprehending both local and global patterns encapsulated in a video, both spatially and temporally. To address the…