Latest 10 Papers - May 04, 2025

by ADMIN 32 views

Latest 10 Papers - May 04, 2025

Graph Foundation Model

Graph foundation models have gained significant attention in recent years due to their ability to learn complex graph representations. These models have been applied to various tasks such as graph classification, clustering, and generation. In this section, we will discuss the latest papers on graph foundation models.

Title Date Comment
GLIP-OOD: Zero-Shot Graph OOD Detection with Foundation Model 2025-04-29
UniGraph2: Learning a Unified Embedding Space to Bind Multimodal Graphs 2025-04-25 WWW 2025
GOFA: A Generative One-For-All Model for Joint Graph Language Modeling 2025-04-24
Designing a reliable lateral movement detector using a graph foundation model 2025-04-18
SAMGPT: Text-free Graph Foundation Model for Multi-domain Pre-training and Cross-domain Adaptation 2025-04-12
Accep...

Accepted by WWW2025 Main Track

RiemannGFM: Learning a Graph Foundation Model from Riemannian Geometry 2025-04-08
Accep...

Accepted by WWW 2025 (Oral)

GraphMaster: Automated Graph Synthesis via LLM Agents in Data-Limited Environments 2025-04-01
A Survey of Cross-domain Graph Learning: Progress and Future Directions 2025-03-14
Towards Graph Foundation Models: A Transferability Perspective 2025-03-12
Graph Foundation Models: Concepts, Opportunities and Challenges 2025-03-10
This ...

This is the author's version of the accepted paper (not the IEEE-published version). Citation information: DOI 10.1109/TPAMI.2025.3548729. For access to the final edited and published article, please follow the link provided: https://ieeexplore.ieee.org/document/10915556

Graph Prompt

Graph prompts have been widely used in various applications such as graph classification, clustering, and generation. In this section, we will discuss the latest papers on graph prompts.

| Title | Date | Comment| --- | --- | --- | | MSCRS: Multi-modal Semantic Graph Prompt Learning Framework for Conversational Recommender Systems | 2025-04-25 | | | Kernel-Aware Graph Prompt Learning for Few-Shot Anomaly Detection | 2025-04-16 |

Accep...

Accepted to AAAI 2025

| | MSCPT: Few-shot Whole Slide Image Classification with Multi-scale and Context-focused Prompt Tuning | 2025-04-07 |
This ...

This work has been submitted to the IEEE TMI for possible publication

| | Assessing SPARQL capabilities of Large Language Models | 2025-04-04 |
Peer ...

Peer reviewed and published at NLP4KGc @ Semantics 2024, see original publication at https://ceur-ws.org/Vol-3874/paper3.pdf . Updated Metadata

| | Krait: A Backdoor Attack Against Graph Prompt Tuning | 2025-03-30 |
Accep...

Accepted by SaTML'2025

| | Question-Aware Knowledge Graph Prompting for Enhancing Large Language Models | 2025-03-30 | | | DP-GPL: Differentially Private Graph Prompt Learning | 2025-03-29 |
Not a...

Not all authors have given their explicit consent

| | Edge Prompt Tuning for Graph Neural Networks | 2025-03-02 |
Accep...

Accepted by ICLR 2025

| | LLM-Empowered Class Imbalanced Graph Prompt Learning for Online Drug Trafficking Detection | 2025-02-28 | | | GraphCLIP: Enhancing Transferability in Graph Foundation Models for Text-Attributed Graphs | 2025-02-24 | Accepted to WWW'25 |

Graph Contrastive Learning

Graph contrastive learning has been widely used in various applications such as graph classification, clustering, and generation. In this section, we will discuss the latest papers on graph contrastive learning.

Title Date Comment
Hierarchical Uncertainty-Aware Graph Neural Network 202504-28
A Generative Graph Contrastive Learning Model with Global Signal 2025-04-25
Simple Graph Contrastive Learning via Fractional-order Neural Diffusion Networks 2025-04-24 Submitted to ICML
Unveiling Contrastive Learning's Capability of Neighborhood Aggregation for Collaborative Filtering 2025-04-14
Accep...

Accepted by SIGIR2025

Incorporating Attributes and Multi-Scale Structures for Heterogeneous Graph Contrastive Learning 2025-04-10
Graph-Based Multimodal Contrastive Learning for Chart Question Answering 2025-04-07
Accep...

Accepted at SIGIR 2025

Squeeze and Excitation: A Weighted Graph Contrastive Learning for Collaborative Filtering 2025-04-06
Accep...

Accepted by SIGIR 2025

MageSQL: Enhancing In-context Learning for Text-to-SQL Applications with Large Language Models 2025-04-02
Brain Network Classification Based on Graph Contrastive Learning and Graph Transformer 2025-04-01
10 pa...

10 pages, 5 figures, uses tikz.sty

GNN-Transformer Cooperative Architecture for Trustworthy Graph Contrastive Learning 2025-03-27
In Pr...

In Proceedings of AAAI 2025

Graph Neural Networks

Graph neural networks have been widely used in various applications such as graph classification, clustering, and generation. In this section, we will discuss the latest papers on graph neural networks.

| Title | Date |
Q&A: Graph Foundation Models, Graph Prompts, and Graph Contrastive Learning

In this article, we will answer some of the most frequently asked questions about graph foundation models, graph prompts, and graph contrastive learning.

Q: What is a graph foundation model?

A: A graph foundation model is a type of machine learning model that is designed to learn complex graph representations. These models have been applied to various tasks such as graph classification, clustering, and generation.

Q: What is graph prompt learning?

A: Graph prompt learning is a type of machine learning approach that involves learning to generate graph prompts that can be used to train graph neural networks. Graph prompts are short text sequences that are used to describe the input graph.

Q: What is graph contrastive learning?

A: Graph contrastive learning is a type of machine learning approach that involves learning to contrastively learn graph representations. This approach involves learning to distinguish between different graph representations.

Q: What are the applications of graph foundation models?

A: Graph foundation models have been applied to various tasks such as graph classification, clustering, and generation. They have also been used in various applications such as social network analysis, recommendation systems, and molecular graph analysis.

Q: What are the challenges of graph foundation models?

A: Some of the challenges of graph foundation models include the need for large amounts of training data, the difficulty of learning complex graph representations, and the need for efficient inference algorithms.

Q: What are the applications of graph prompts?

A: Graph prompts have been applied to various tasks such as graph classification, clustering, and generation. They have also been used in various applications such as social network analysis, recommendation systems, and molecular graph analysis.

Q: What are the challenges of graph prompts?

A: Some of the challenges of graph prompts include the need for large amounts of training data, the difficulty of learning complex graph representations, and the need for efficient inference algorithms.

Q: What are the applications of graph contrastive learning?

A: Graph contrastive learning has been applied to various tasks such as graph classification, clustering, and generation. It has also been used in various applications such as social network analysis, recommendation systems, and molecular graph analysis.

Q: What are the challenges of graph contrastive learning?

A: Some of the challenges of graph contrastive learning include the need for large amounts of training data, the difficulty of learning complex graph representations, and the need for efficient inference algorithms.

Q: How can I get started with graph foundation models, graph prompts, and graph contrastive learning?

A: To get started with graph foundation models, graph prompts, and graph contrastive learning, you can start by reading the latest papers on these topics. You can also try implementing some of the algorithms and techniques described in these papers using popular machine learning frameworks such as PyTorch and TensorFlow.

Q: What are some of the popular tools and libraries for graph foundation models, graph prompts, and graph contrastive learning?

A: Some of the popular tools and libraries for graph foundation models, graph prompts, and graph contrastive learning include PyTorch Geometric, TensorFlow Graph, and GraphSAGE.

Q: What are some of the future directions for graph models, graph prompts, and graph contrastive learning?

A: Some of the future directions for graph foundation models, graph prompts, and graph contrastive learning include the development of more efficient inference algorithms, the use of graph foundation models in more applications, and the development of more robust and interpretable graph prompts.

We hope that this Q&A article has been helpful in answering some of the most frequently asked questions about graph foundation models, graph prompts, and graph contrastive learning. If you have any further questions, please don't hesitate to ask.