Search Results for author:
Found 14 papers, 7 papers with code
All in One: Multi-Task Prompting for Graph Neural Networks (Extended Abstract)
This paper is an extended abstract of our original work published in KDD23, where we won the best research paper award (Xiangguo Sun, Hong Cheng, Jia Li, Bo Liu, and Jihong Guan.
DDIPrompt: Drug-Drug Interaction Event Prediction based on Graph Prompt Learning
(2) the scarcity of labeled data for rare events, which is a pervasive issue in the medical field where rare yet potentially critical interactions are often overlooked or under-studied due to limited available data.
All in One and One for All: A Simple yet Effective Method towards Cross-domain Graph Pretraining
In response to this challenge, we propose a novel approach called Graph COordinators for PrEtraining (GCOPE), that harnesses the underlying commonalities across diverse graph datasets to enhance few-shot learning.
Prompt Learning on Temporal Interaction Graphs
In detail, we propose a temporal prompt generator to offer temporally-aware prompts for different tasks.
Attention Is Not the Only Choice: Counterfactual Reasoning for Path-Based Explainable Recommendation
Unfortunately, these attention weights are intentionally designed for model accuracy but not explainability.
Graph Prompt Learning: A Comprehensive Survey and Beyond
This paper presents a pioneering survey on the emerging domain of graph prompts in AGI, addressing key challenges and opportunities in harnessing graph data for AGI applications.
A Survey of Graph Meets Large Language Model: Progress and Future Directions
First of all, we propose a new taxonomy, which organizes existing methods into three categories based on the role (i. e., enhancer, predictor, and alignment component) played by LLMs in graph-related tasks.
Counter-Empirical Attacking based on Adversarial Reinforcement Learning for Time-Relevant Scoring System
To establish such scoring systems, several "empirical criteria" are firstly determined, followed by dedicated top-down design for each factor of the score, which usually requires enormous effort to adjust and tune the scoring function in the new application scenario.
All in One: Multi-task Prompting for Graph Neural Networks
Inspired by the prompt learning in natural language processing (NLP), which has presented significant effectiveness in leveraging prior knowledge for various NLP tasks, we study the prompting topic for graphs with the motivation of filling the gap between pre-trained models and various graph tasks.
Generating Counterfactual Hard Negative Samples for Graph Contrastive Learning
In this paper, we propose a novel method to utilize \textbf{C}ounterfactual mechanism to generate artificial hard negative samples for \textbf{G}raph \textbf{C}ontrastive learning, namely \textbf{CGC}, which has a different perspective compared to those sampling-based strategies.
Graph Masked Autoencoders with Transformers
In this paper, we propose Graph Masked Autoencoders (GMAEs), a self-supervised transformer-based model for learning graph representations.
Unsupervised Graph Poisoning Attack via Contrastive Loss Back-propagation
Extensive experiments show that our attack outperforms unsupervised baseline attacks and has comparable performance with supervised attacks in multiple downstream tasks including node classification and link prediction.
Temporal Meta-path Guided Explainable Recommendation
This paper utilizes well-designed item-item path modelling between consecutive items with attention mechanisms to sequentially model dynamic user-item evolutions on dynamic knowledge graph for explainable recommendations.
Social and Information Networks
Multi-level Graph Convolutional Networks for Cross-platform Anchor Link Prediction
Moreover, to adapt the proposed method to be capable of handling large-scale social networks, we propose a two-phase space reconciliation mechanism to align the embedding spaces in both network partitioning based parallel training and account matching across different social networks.
