Related papers: Beyond the Aggregation Dilemma: Prior-Retaining De…

Large language models (LLMs) still struggle with multi-hop reasoning over knowledge-graphs (KGs), and we identify a previously overlooked structural reason for this difficulty: Transformer attention heads naturally specialize in distinct…

Large multimodal models (LMMs) have exhibited proficiencies across many visual tasks. Although numerous well-known benchmarks exist to evaluate model performance, they increasingly have insufficient headroom. As such, there is a pressing…

Large Language Models (LLMs) integrated with Retrieval-Augmented Generation (RAG) techniques have exhibited remarkable performance across a wide range of domains. However, existing RAG approaches primarily operate on unstructured data and…

Multimodal Large Language Models (MLLMs) demonstrate exceptional semantic reasoning but struggle with 3D spatial perception when restricted to pure RGB inputs. Despite leveraging implicit geometric priors from 3D reconstruction models,…

Graph Representation Learning (GRL) can be fundamentally modeled as a physical process of seeking an energy equilibrium state for a node system on a latent manifold. However, existing Graph Neural Networks (GNNs) often suffer from…

Despite the strong abilities, large language models (LLMs) still suffer from hallucinations and reliance on outdated knowledge, raising concerns in knowledge-intensive tasks. Graph-based retrieval-augmented generation (GRAG) enriches LLMs…

Continuous graph neural models based on differential equations have expanded the architecture of graph neural networks (GNNs). Due to the connection between graph diffusion and message passing, diffusion-based models have been widely…

Continual Graph Learning(CGL)focuses on acquiring new knowledge while retaining previously learned information, essential for real-world graph applications. Current methods grapple with two main issues:1) The Stability-Plasticity Dilemma:…

Learning a graph topology to reveal the underlying relationship between data entities plays an important role in various machine learning and data analysis tasks. Under the assumption that structured data vary smoothly over a graph, the…

Self-attention mechanism in graph neural networks (GNNs) led to state-of-the-art performance on many graph representation learning tasks. Currently, at every layer, attention is computed between connected pairs of nodes and depends solely…

Large language models (LLMs) have demonstrated remarkable capabilities in a wide range of tasks, yet their application to specialized domains remains challenging due to the need for deep expertise. Retrieval-Augmented generation (RAG) has…

Graph neural networks (GNNs) manifest pathologies including over-smoothing and limited discriminating power as a result of suboptimally expressive aggregating mechanisms. We herein present a unifying framework for stochastic aggregation…

Recent advancements in Graph Contrastive Learning (GCL) have demonstrated remarkable effectiveness in improving graph representations. However, relying on predefined augmentations (e.g., node dropping, edge perturbation, attribute masking)…

Link prediction is a fundamental problem in many graph based applications, such as protein-protein interaction prediction. Graph neural network (GNN) has recently been widely used for link prediction. However, existing GNN based link…

Graph representation learning, involving both node features and graph structures, is crucial for real-world applications but often encounters pervasive noise. State-of-the-art methods typically address noise by focusing separately on node…

Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in representing and understanding diverse modalities. However, they typically focus on modality alignment in a pairwise manner while overlooking structural…

Disentangled representation learning (DRL) aims to identify and decompose underlying factors behind observations, thus facilitating data perception and generation. However, current DRL approaches often rely on the unrealistic assumption…

Surgical workflow recognition is vital for automating tasks, supporting decision-making, and training novice surgeons, ultimately improving patient safety and standardizing procedures. However, data corruption can lead to performance…

Traditional Machine Learning (ML) methods require large amounts of data to perform well, limiting their applicability in sparse or incomplete scenarios and forcing the usage of additional synthetic data to improve the model training. To…

In practical applications, multi-view data depicting objectives from assorted perspectives can facilitate the accuracy increase of learning algorithms. However, given multi-view data, there is limited work for learning discriminative node…