Related papers: Modality as Heterogeneity: Node Splitting and Grap…

Time-independent Partial Differential Equations (PDEs) on large meshes pose significant challenges for data-driven neural PDE solvers. We introduce a novel graph rewiring technique to tackle some of these challenges, such as aggregating…

Learning high-quality multi-modal entity representations is an important goal of multi-modal knowledge graph (MMKG) representation learning, which can enhance reasoning tasks within the MMKGs, such as MMKG completion (MMKGC). The main…

Mixture-of-Experts (MoE) architectures have emerged as a powerful paradigm for scaling neural networks while maintaining computational efficiency. However, standard MoE implementations rely on two rigid design assumptions: (1) fixed Top-K…

Knowledge graphs enable data scientists to learn end-to-end on heterogeneous knowledge. However, most end-to-end models solely learn from the relational information encoded in graphs' structure: raw values, encoded as literal nodes, are…

Multimodal Sentiment Analysis (MSA) is a rapidly developing field that integrates multimodal information to recognize sentiments, and existing models have made significant progress in this area. The central challenge in MSA is multimodal…

In the trend of hybrid Artificial Intelligence techniques, Physical-Informed Machine Learning has seen a growing interest. It operates mainly by imposing data, learning, or architecture bias with simulation data, Partial Differential…

Unsupervised multimodal change detection is a practical and challenging topic that can play an important role in time-sensitive emergency applications. To address the challenge that multimodal remote sensing images cannot be directly…

Multi-modal stance detection (MSD) aims to determine an author's stance toward a given target using both textual and visual content. While recent methods leverage multi-modal fusion and prompt-based learning, most fail to distinguish…

Real-world model deployment across multiple domains requires multimodal models to operate under two complementary regimes: (1) multi-task pretraining, tasks are co-available at design time where related tasks could borrow representational…

Hard-parameter sharing is a common strategy to train a single model jointly across diverse tasks. However, this often leads to task interference, impeding overall model performance. To address the issue, we propose a simple yet effective…

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…

Transformer models based on the Mixture of Experts (MoE) architecture have made significant progress in long-sequence modeling, but existing models still have shortcomings in computational efficiency and the ability to capture long-range…

As various types of crime continue to threaten public safety and economic development, predicting the occurrence of multiple types of crimes becomes increasingly vital for effective prevention measures. Although extensive efforts have been…

Multimodal recommender systems amalgamate multimodal information (e.g., textual descriptions, images) into a collaborative filtering framework to provide more accurate recommendations. While the incorporation of multimodal information could…

The field of natural language processing (NLP) has made significant strides in recent years, particularly in the development of large-scale vision-language models (VLMs). These models aim to bridge the gap between text and visual…

Heterogeneous information network (HIN) has been widely used to characterize entities of various types and their complex relations. Recent attempts either rely on explicit path reachability to leverage path-based semantic relatedness or…

Graph clustering, aiming to partition nodes of a graph into various groups via an unsupervised approach, is an attractive topic in recent years. To improve the representative ability, several graph auto-encoder (GAE) models, which are based…

Efficiency, specialization, and adaptability to new data distributions are qualities that are hard to combine in current Large Language Models. The Mixture of Experts (MoE) architecture has been the focus of significant research because its…

Mixture-of-Experts (MoE) architectures achieve parameter efficiency through conditional computation, yet contemporary designs suffer from two fundamental limitations: structural parameter isolation that causes catastrophic forgetting, and…

Sparsely Mixture of Experts (MoE) has received great interest due to its promising scaling capability with affordable computational overhead. MoE converts dense layers into sparse experts, and utilizes a gated routing network to make…