Trajectory generation and trajectory prediction are two critical tasks f...
Personalized recommender systems play a crucial role in capturing users'...
Federated learning (FL) enables collaborative model training across
dist...
Graph Neural Networks (GNNs) have demonstrated superior performance on
v...
Self-supervised learning (SSL) has gained significant interest in recent...
We propose DAVIS, a Diffusion model-based Audio-VIusal Separation framew...
Random forest is effective for prediction tasks but the randomness of tr...
In this paper, we introduce a new self-supervised rationalization method...
Medical image segmentation of gadolinium enhancement magnetic resonance
...
Spatial-temporal graph learning has emerged as a promising solution for
...
Open-set fine-grained anomaly detection is a challenging task that requi...
Traffic forecasting plays a critical role in smart city initiatives and ...
This paper presents a novel approach to representation learning in
recom...
Social recommendation is gaining increasing attention in various online
...
Recently, graph neural networks (GNNs) have been successfully applied to...
While some powerful neural network architectures (e.g., Transformer, Gra...
Recent studies show that graph neural networks (GNNs) are prevalent to m...
Neural networks (NNs) playing the role of controllers have demonstrated
...
Humanitarian agencies must be prepared to mobilize quickly in response t...
Humans naturally perceive surrounding scenes by unifying sound and sight...
Current sequential recommender systems are proposed to tackle the dynami...
Graph neural networks (GNNs) have shown the power in representation lear...
Social recommender systems have drawn a lot of attention in many online ...
Graph neural networks (GNNs) have emerged as the state-of-the-art paradi...
Graph Neural Networks (GNNs) have become powerful tools in modeling
grap...
The online emergence of multi-modal sharing platforms (eg, TikTok, Youtu...
Recommender systems have been demonstrated to be effective to meet user'...
Graph neural network (GNN) is a powerful learning approach for graph-bas...
Human perception of the complex world relies on a comprehensive analysis...
Spatio-temporal graph neural networks (STGNN) have become the most popul...
Robust prediction of citywide traffic flows at different time periods pl...
Federated Learning (FL) is a distributed machine learning paradigm where...
Detecting anomalous trajectories has become an important task in many
lo...
Even pruned by the state-of-the-art network compression methods, Graph N...
It is quite challenging to ensure the safety of reinforcement learning (...
With the increment of interest in leveraging machine learning technology...
Heterogeneous graph convolutional networks have gained great popularity ...
Incomplete multi-view clustering, which aims to solve the clustering pro...
Graph Neural Networks (GNNs) have been shown as promising solutions for
...
Learning dynamic user preference has become an increasingly important
co...
Federated learning (FL) is an emerging technology that enables the train...
Modeling time-evolving preferences of users with their sequential item
i...
Recipe recommendation systems play an essential role in helping people d...
Trajectory-User Linking (TUL), which links trajectories to users who gen...
Knowledge Graphs (KGs) have been utilized as useful side information to
...
Collaborative Filtering (CF) has emerged as fundamental paradigms for
pa...
One fundamental problem in temporal graph analysis is to count the
occur...
Crime has become a major concern in many cities, which calls for the ris...
Deep learning techniques for point clouds have achieved strong performan...
The robustness of deep neural networks has received significant interest...