Related papers: MUG: Meta-path-aware Universal Heterogeneous Graph…

In this paper, we introduce a self-supervised learning method to enhance the graph-level representations with the help of a set of subgraphs. For this purpose, we propose a universal framework to generate subgraphs in an auto-regressive way…

Multimodal graphs, which integrate unstructured heterogeneous data with structured interconnections, offer substantial real-world utility but remain insufficiently explored in unsupervised learning. In this work, we initiate the study of…

Since real-world objects and their interactions are often multi-modal and multi-typed, heterogeneous networks have been widely used as a more powerful, realistic, and generic superclass of traditional homogeneous networks (graphs).…

Deep learning models often struggle to maintain generalizability in medical imaging, particularly under domain-fracture scenarios where distribution shifts arise from varying imaging techniques, acquisition protocols, patient populations,…

This work addresses a fundamental challenge in applying deep learning to power systems: developing neural network models that transfer across significant system changes, including networks with entirely different topologies and…

Multimodal graphs are gaining increasing attention due to their rich representational power and wide applicability, yet they introduce substantial challenges arising from severe modality confusion. To address this issue, we propose NSG…

In heterogeneous graphs, we can observe complex structures such as tree-like or hierarchical structures. Recently, the hyperbolic space has been widely adopted in many studies to effectively learn these complex structures. Although these…

Graphs are a natural representation for systems based on relations between connected entities. Combinatorial optimization problems, which arise when considering an objective function related to a process of interest on discrete structures,…

Data association is at the core of many computer vision tasks, e.g., multiple object tracking, image matching, and point cloud registration. however, current data association solutions have some defects: they mostly ignore the intra-view…

Recent advances in generic large models, such as GPT and DeepSeek, have motivated the introduction of universality to graph pre-training, aiming to learn rich and generalizable knowledge across diverse domains using graph representations to…

Graph foundation models have recently attracted significant attention due to its strong generalizability. Although existing methods resort to language models to learn unified semantic representations across domains, they disregard the…

Recently, transformers have shown promising performance in learning graph representations. However, there are still some challenges when applying transformers to real-world scenarios due to the fact that deep transformers are hard to train…

Composed Image Retrieval (CIR) enables image search by combining a reference image with modification text. Intrinsic noise in CIR triplets incurs intrinsic uncertainty and threatens the model's robustness. Probabilistic learning approaches…

Due to its complexity, graph learning-based multi-modal integration and classification is one of the most challenging obstacles for disease prediction. To effectively offset the negative impact between modalities in the process of…

Multi-modal neural machine translation (NMT) aims to translate source sentences into a target language paired with images. However, dominant multi-modal NMT models do not fully exploit fine-grained semantic correspondences between semantic…

Albeit having gained significant progress lately, large-scale graph representation learning remains expensive to train and deploy for two main reasons: (i) the repetitive computation of multi-hop message passing and non-linearity in graph…

In the digital era, users typically interact with diverse items across multiple domains (e.g., e-commerce, streaming platforms, and social networks), generating intricate heterogeneous interaction graphs. Leveraging multi-domain data can…

Recent years have witnessed the rapid development of heterogeneous graph neural networks (HGNNs) in information retrieval (IR) applications. Many existing HGNNs design a variety of tailor-made graph convolutions to capture structural and…

Numerical simulation of multi-phase fluid dynamics in porous media is critical to a variety of geoscience applications. Data-driven surrogate models using Convolutional Neural Networks (CNNs) have shown promise but are constrained to…

Biological intelligence systems of animals perceive the world by integrating information in different modalities and processing simultaneously for various tasks. In contrast, current machine learning research follows a task-specific…