Related papers: Modality-Guided Mixture of Graph Experts with Entr…

Recently, real-world recommendation systems need to deal with millions of candidates. It is extremely challenging to conduct sophisticated end-to-end algorithms on the entire corpus due to the tremendous computation costs. Therefore,…

In recent years, deep learning (DL)-based methods have been widely used in code vulnerability detection. The DL-based methods typically extract structural information from source code, e.g., code structure graph, and adopt neural networks…

Mixture-of-Experts (MoE) offers flexible graph reasoning by combining multiple views of a graph through a learned router. We investigate routing-aware explanations for MoE graph models in malware detection using control flow graphs (CFGs).…

Dynamic Text-Attributed Graphs (DyTAGs) are a novel graph paradigm that captures evolving temporal events (edges) alongside rich textual attributes. Existing studies can be broadly categorized into TGNN-driven and LLM-driven approaches,…

The rise of 5G/6G network technologies promises to enable applications like autonomous vehicles and virtual reality, resulting in a significant increase in connected devices and necessarily complicating network management. Even worse, these…

With the progress of the urbanisation process, the urban transportation system is extremely critical to the development of cities and the quality of life of the citizens. Among them, it is one of the most important tasks to judge traffic…

Multivariate time series (MTS) forecasting plays an important role in the automation and optimization of intelligent applications. It is a challenging task, as we need to consider both complex intra-variable dependencies and inter-variable…

Accurately identifying gas mixtures and estimating their concentrations are crucial across various industrial applications using gas sensor arrays. However, existing models face challenges in generalizing across heterogeneous datasets,…

Bundle recommendations strive to offer users a set of items as a package named bundle, enhancing convenience and contributing to the seller's revenue. While previous approaches have demonstrated notable performance, we argue that they may…

Realistic graphs contain both (1) rich self-features of nodes and (2) informative structures of neighborhoods, jointly handled by a Graph Neural Network (GNN) in the typical setup. We propose to decouple the two modalities by Mixture of…

Multimodal brain networks characterize complex connectivities among different brain regions from both structural and functional aspects and provide a new means for mental disease analysis. Recently, Graph Neural Networks (GNNs) have become…

Many previous studies aim to augment collaborative filtering with deep neural network techniques, so as to achieve better recommendation performance. However, most existing deep learning-based recommender systems are designed for modeling…

While hardware-software co-design has significantly improved the efficiency of neural network inference, modeling the training phase remains a critical yet underexplored challenge. Training workloads impose distinct constraints,…

Multimodal recommendation systems are increasingly popular for their potential to improve performance by integrating diverse data types. However, the actual benefits of this integration remain unclear, raising questions about when and how…

Multiple object tracking (MOT) is a significant task in achieving autonomous driving. Traditional works attempt to complete this task, either based on point clouds (PC) collected by LiDAR, or based on images captured from cameras. However,…

Combining complementary information from multiple modalities is intuitively appealing for improving the performance of learning-based approaches. However, it is challenging to fully leverage different modalities due to practical challenges…

Artificial intelligence for graphs has achieved remarkable success in modeling complex systems, ranging from dynamic networks in biology to interacting particle systems in physics. However, the increasingly heterogeneous graph datasets call…

Existing text-driven infrared and visible image fusion approaches often rely on textual information at the sentence level, which can lead to semantic noise from redundant text and fail to fully exploit the deeper semantic value of textual…

Modern recommender systems often embed users and items into low-dimensional latent representations, based on their observed interactions. In practical recommendation scenarios, users often exhibit various intents which drive them to…

Trajectory prediction is critical for applications of planning safe future movements and remains challenging even for the next few seconds in urban mixed traffic. How an agent moves is affected by the various behaviors of its neighboring…