most citedInductive Graph Alignment Prompt: Bridging the Gap between Graph Pre-training and Inductive Fine-tuning From Spectral Perspective

18 citations · 25 across the 6 of their papers we have counts for

collaborators

6 papers

cs.LG2024

Towards Graph Prompt Learning: A Survey and Beyond

Qingqing Long, Yuchen Yan, Peiyan Zhang +12

Large-scale "pre-train and prompt learning" paradigms have demonstrated remarkable adaptability, enabling broad applications across diverse domains such as question answering, imag…

cs.LG202418 cited

Inductive Graph Alignment Prompt: Bridging the Gap between Graph Pre-training and Inductive Fine-tuning From Spectral Perspective

Yuchen Yan, Peiyan Zhang, Zheng Fang +1

The "Graph pre-training and fine-tuning" paradigm has significantly improved Graph Neural Networks(GNNs) by capturing general knowledge without manual annotations for downstream ta…

cs.IR2024

High-Frequency-aware Hierarchical Contrastive Selective Coding for Representation Learning on Text-attributed Graphs

Peiyan Zhang, Chaozhuo Li, Liying Kang +4

We investigate node representation learning on text-attributed graphs (TAGs), where nodes are associated with text information. Although recent studies on graph neural networks (GN…

cs.IR2023

Exploring Recommendation Capabilities of GPT-4V(ision): A Preliminary Case Study

Peilin Zhou, Meng Cao, You-Liang Huang +6

Large Multimodal Models (LMMs) have demonstrated impressive performance across various vision and language tasks, yet their potential applications in recommendation tasks with visu…

cs.IR20231 cited

CDR-Adapter: Learning Adapters to Dig Out More Transferring Ability for Cross-Domain Recommendation Models

Yanyu Chen, Yao Yao, Wai Kin Victor Chan +4

Data sparsity and cold-start problems are persistent challenges in recommendation systems. Cross-domain recommendation (CDR) is a promising solution that utilizes knowledge from th…

cs.IR20236 cited

A Survey on Incremental Update for Neural Recommender Systems

Peiyan Zhang, Sunghun Kim

Recommender Systems (RS) aim to provide personalized suggestions of items for users against consumer over-choice. Although extensive research has been conducted to address differen…