Related papers: OptiMAG: Structure-Semantic Alignment via Unbalanc…
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…
Multimodal dialogue emotion recognition captures emotional cues by fusing text, visual, and audio modalities. However, existing approaches still suffer from notable limitations in modeling emotional dependencies and learning multimodal…
Multimodal representation learning aims to capture both shared and complementary semantic information across multiple modalities. However, the intrinsic heterogeneity of diverse modalities presents substantial challenges to achieve…
Prevailing methods for integrating graphs into Language Models (LMs) typically rely on a segregated architecture: external Graph Neural Networks (GNNs) encode structural topology, while LMs process textual semantics. We argue this approach…
Recent studies of federated graph foundational models (FedGFMs) break the idealized and untenable assumption of having centralized data storage to train graph foundation models, and accommodate the reality of distributed, privacy-restricted…
Current Retrieval-Augmented Generation (RAG) systems primarily operate on unimodal textual data, limiting their effectiveness on unstructured multimodal documents. Such documents often combine text, images, tables, equations, and graphs,…
The quest for accurate prediction of drug molecule properties poses a fundamental challenge in the realm of Artificial Intelligence Drug Discovery (AIDD). An effective representation of drug molecules emerges as a pivotal component in this…
Pre-training Graph Foundation Models (GFMs) on text-attributed graphs (TAGs) is central to web-scale applications such as search, recommendation, and knowledge discovery. However, existing CLIP-style graph-text aligners face two key…
Graph Retrieval-Augmented Generation (GRAG or Graph RAG) architectures aim to enhance language understanding and generation by leveraging external knowledge. However, effectively capturing and integrating the rich semantic information…
Dynamic text-attributed graphs (DyTAGs) provide a powerful framework for modeling evolving systems in which node semantics and time-dependent interactions are tightly coupled. Recently, multimodal learning has emerged as a promising yet…
Finding node correspondence across networks, namely multi-network alignment, is an essential prerequisite for joint learning on multiple networks. Despite great success in aligning networks in pairs, the literature on multi-network…
We present a framework for embedding graph structured data into a vector space, taking into account node features and topology of a graph into the optimal transport (OT) problem. Then we propose a novel distance between two graphs, named…
Understanding how brain structure and function interact is key to explaining intelligence yet modeling them jointly is challenging as the structural and functional connectome capture complementary aspects of organization. We introduced…
Root-mean-square deviation (RMSD) is widely used to assess structural similarity in systems ranging from flexible ligand conformers to complex molecular cluster configurations. Despite its wide utility, RMSD calculation is often challenged…
Multi-modal entity alignment (MMEA) aims to identify equivalent entities between two multi-modal knowledge graphs (MMKGs), whose entities can be associated with relational triples and related images. Most previous studies treat the graph…
The similarity of graph structures, such as Meaning Representations (MRs), is often assessed via structural matching algorithms, such as Smatch (Cai and Knight, 2013). However, Smatch involves a combinatorial problem that suffers from…
Graphs are the most ubiquitous data structures for representing relational datasets and performing inferences in them. They model, however, only pairwise relations between nodes and are not designed for encoding the higher-order relations.…
Graph data augmentation has shown superiority in enhancing generalizability and robustness of GNNs in graph-level classifications. However, existing methods primarily focus on the augmentation in the graph signal space and the graph…
Multimodal Knowledge Graphs (MMKGs), which represent explicit knowledge across multiple modalities, play a pivotal role by complementing the implicit knowledge of Multimodal Large Language Models (MLLMs) and enabling more grounded reasoning…
The design of artificial neural networks (ANNs) is inspired by the structure of the human brain, and in turn, ANNs offer a potential means to interpret and understand brain signals. Existing methods primarily align brain signals with…