Latest 10 Papers - May 14, 2025

by ADMIN 32 views

Latest 10 Papers - May 14, 2025

Graph Foundation Model

The Graph Foundation Model has been a rapidly evolving field in recent years, with numerous breakthroughs and advancements in various aspects of graph learning. In this section, we will highlight the latest 10 papers in the field of Graph Foundation Model, covering topics such as graph contrastive learning, graph prompt learning, and graph neural networks.

Title Date Comment
InfoNCE is a Free Lunch for Semantically guided Graph Contrastive Learning 2025-05-07
10 pa...

10 pages, 5 figures, Accepted by SIGIR2025

A Survey on Self-Supervised Graph Foundation Models: Knowledge-Based Perspective 2025-05-06
Accep...

Accepted by TKDE; full version (27 pages, 9 figures)

GraphMaster: Automated Graph Synthesis via LLM Agents in Data-Limited Environments 2025-05-05
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)

A Survey of Cross-domain Graph Learning: Progress and Future Directions 2025-03-14

Graph Prompt

Graph prompt learning has emerged as a crucial aspect of graph learning, enabling the efficient and effective learning of graph models. In this section, we will highlight the latest 10 papers in the field of graph prompt learning, covering topics such as graph prompt optimization, graph prompt tuning, and graph prompt evaluation.

Title Date Comment
Vision Graph Prompting via Semantic Low-Rank Decomposition 2025-05-07
Accep...

Accepted by ICML 2025

ReGraP-LLaVA: Reasoning enabled Graph-based Personalized Large Language and Vision Assistant 2025-05-06 Work in progress
GraphPrompter: Multi-stage Adaptive Prompt Optimization for Graph In-Context Learning 2025-05-04
14 pa...

14 pages. IEEE International Conference on Data Engineering (ICDE'2025), accepted

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

Graph Contrastive Learning

Graph contrastive learning has emerged as a crucial aspect of graph learning, enabling the efficient and effective learning of graph models. In this section, we will highlight the latest 10 papers in the field of graph contrastive learning, covering topics such as graph contrastive learning, graph contrastive loss, and graph contrastive evaluation.

Title Date Comment
Rethinking Graph Contrastive Learning through Relative Similarity Preservation 2025-05-12
Accep...

Accepted by IJCAI2025; full version including appendix

InfoNCE is a Free Lunch for Semantically guided Graph Contrastive Learning 2025-05-07
10 pa...

10 pages, 5 figures, Accepted by SIGIR2025

Quantum Rationale-Aware Graph Contrastive Learning for Jet Discrimination 2025-05-04
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

Q&A: Graph Foundation Model, Graph Prompt, and Graph Contrastive Learning

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

Q: What is graph foundation model?

A: Graph foundation model is a type of machine learning model that is designed to learn and represent graph-structured data. Graph-structured data is a type of data that is composed of nodes and edges, and is commonly used in applications such as social network analysis, recommendation systems, and molecular biology.

Q: What is graph prompt?

A: Graph prompt is a type of input that is used to guide the learning of a graph model. Graph prompts are typically short text sequences that are used to provide context and information to the model, and are commonly used in applications such as graph-based question answering and graph-based recommendation systems.

Q: What is graph contrastive learning?

A: Graph contrastive learning is a type of machine learning algorithm that is designed to learn and represent graph-structured data. Graph contrastive learning algorithms work by contrasting positive and negative examples of graph-structured data, and are commonly used in applications such as graph-based recommendation systems and graph-based anomaly detection.

Q: What are the benefits of graph foundation model?

A: The benefits of graph foundation model include:

  • Improved accuracy and performance on graph-structured data
  • Ability to learn and represent complex graph structures
  • Ability to handle large and diverse datasets
  • Ability to be used in a variety of applications, including recommendation systems, social network analysis, and molecular biology

Q: What are the benefits of graph prompt?

A: The benefits of graph prompt include:

  • Improved accuracy and performance on graph-based tasks
  • Ability to provide context and information to the model
  • Ability to be used in a variety of applications, including graph-based question answering and graph-based recommendation systems
  • Ability to be used in conjunction with other machine learning algorithms and techniques

Q: What are the benefits of graph contrastive learning?

A: The benefits of graph contrastive learning include:

  • Improved accuracy and performance on graph-structured data
  • Ability to learn and represent complex graph structures
  • Ability to handle large and diverse datasets
  • Ability to be used in a variety of applications, including graph-based recommendation systems and graph-based anomaly detection

Q: What are some common applications of graph foundation model?

A: Some common applications of graph foundation model include:

  • Recommendation systems
  • Social network analysis
  • Molecular biology
  • Graph-based question answering
  • Graph-based recommendation systems

Q: What are some common applications of graph prompt?

A: Some common applications of graph prompt include:

  • Graph-based question answering
  • Graph-based recommendation systems
  • Graph-based anomaly detection
  • Graph-based clustering
  • Graph-based classification

Q: What are some common applications of graph contrastive learning?

A: Some common applications of graph contrastive learning include:

  • Graph-based recommendation systems
  • Graph-based anomaly detection
  • Graph-based clustering
  • Graph-based classification
  • Graph-based regression

Q: What are some challenges associated with graph foundation model?

A: Some challenges associated with graph foundation model include:

  • Difficulty in large and diverse datasets
  • Difficulty in learning and representing complex graph structures
  • Difficulty in handling noisy and missing data
  • Difficulty in evaluating and comparing the performance of different graph models

Q: What are some challenges associated with graph prompt?

A: Some challenges associated with graph prompt include:

  • Difficulty in designing and selecting effective graph prompts
  • Difficulty in handling noisy and missing data
  • Difficulty in evaluating and comparing the performance of different graph prompts
  • Difficulty in handling large and diverse datasets

Q: What are some challenges associated with graph contrastive learning?

A: Some challenges associated with graph contrastive learning include:

  • Difficulty in handling large and diverse datasets
  • Difficulty in learning and representing complex graph structures
  • Difficulty in handling noisy and missing data
  • Difficulty in evaluating and comparing the performance of different graph contrastive learning algorithms

Q: What are some future directions for graph foundation model?

A: Some future directions for graph foundation model include:

  • Developing more effective and efficient graph models
  • Developing more effective and efficient graph prompts
  • Developing more effective and efficient graph contrastive learning algorithms
  • Applying graph foundation model to new and emerging applications

Q: What are some future directions for graph prompt?

A: Some future directions for graph prompt include:

  • Developing more effective and efficient graph prompts
  • Developing more effective and efficient graph models
  • Developing more effective and efficient graph contrastive learning algorithms
  • Applying graph prompt to new and emerging applications

Q: What are some future directions for graph contrastive learning?

A: Some future directions for graph contrastive learning include:

  • Developing more effective and efficient graph contrastive learning algorithms
  • Developing more effective and efficient graph models
  • Developing more effective and efficient graph prompts
  • Applying graph contrastive learning to new and emerging applications