RAGraph: A General Retrieval-Augmented Graph Learning Framework
Graph Neural Networks (GNNs) have become essential in interpreting relational data across
various domains, yet, they often struggle to generalize to unseen graph data that differs …
various domains, yet, they often struggle to generalize to unseen graph data that differs …
Organizing Unstructured Image Collections using Natural Language
Organizing unstructured visual data into semantic clusters is a key challenge in computer
vision. Traditional deep clustering (DC) approaches focus on a single partition of data, while …
vision. Traditional deep clustering (DC) approaches focus on a single partition of data, while …
Retrieval-Augmented Dynamic Prompt Tuning for Incomplete Multimodal Learning
Multimodal learning with incomplete modality is practical and challenging. Recently,
researchers have focused on enhancing the robustness of pre-trained MultiModal …
researchers have focused on enhancing the robustness of pre-trained MultiModal …
Bridging the User-side Knowledge Gap in Knowledge-aware Recommendations with Large Language Models
In recent years, knowledge graphs have been integrated into recommender systems as item-
side auxiliary information, enhancing recommendation accuracy. However, constructing and …
side auxiliary information, enhancing recommendation accuracy. However, constructing and …
Unsupervised Adaptive Hypergraph Correlation Hashing for multimedia retrieval
Y Chen, Y Long, Z Yang, J Long - Information Processing & Management, 2025 - Elsevier
Cross-modal hashing has attracted widespread attention from researchers due to its
capabilities to handle large volumes of heterogeneous multimedia information with fast …
capabilities to handle large volumes of heterogeneous multimedia information with fast …
Natural Evolution-based Dual-Level Aggregation for Temporal Knowledge Graph Reasoning
Temporal knowledge graph (TKG) reasoning aims to predict missing facts based on a given
history. Most of the existing methods unifiedly model the evolution process of different events …
history. Most of the existing methods unifiedly model the evolution process of different events …
Multimodal RAG Analysis of Product Datasheet
Large language models such as ChatGPT serves as multipurpose chatbot that can provide
information across diverse disciplines. However, in order to generate timely and accurate …
information across diverse disciplines. However, in order to generate timely and accurate …
Organizing Unstructured Image Collections using Natural Language
B Biased - openreview.net
Organizing unstructured visual data into semantic clusters is a key challenge in computer
vision. Traditional deep clustering (DC) approaches focus on a single partition of data, while …
vision. Traditional deep clustering (DC) approaches focus on a single partition of data, while …
Multi-Message Iterative Propagation Model Based on Explicit-Implicit Feature Mining
R Wang, Z Wang, S Wei, S Duan, Y **ao - papers.ssrn.com
Trending topics on social media often spark secondary discussions that can evolve into
rumors or negative opinions, impacting social harmony. This study investigates individual …
rumors or negative opinions, impacting social harmony. This study investigates individual …