1 citations · 1 across the 11 of their papers we have counts for
12 papers
Learning the Latent Structure: A Feature-Centric Approach to Graph Data Augmentation
Yu Song, Zhigang Hua, Yan Xie +5
Graph-structured data plays a pivotal role in modeling complex relationships. However, real-world graphs are often incomplete due to data collection and observational constraints,…
Beyond Fixed Depths and Widths: Optimizing Textual Decoding Tries in LLM-based Generative Recommendation
Jingzhe Liu, Hanbing Wang, Jiliang Tang +4
Generative recommendation (GR) is an increasingly popular paradigm in recommender systems, with a prominent line of work using LLMs as autoregressive backbones to predict the next…
Understanding Generative Recommendation with Semantic IDs from a Model-scaling View
Jingzhe Liu, Liam Collins, Jiliang Tang +3
Recent advancements in generative models have allowed the emergence of a promising paradigm for recommender systems (RS), known as Generative Recommendation (GR), which tries to un…
GSTBench: A Benchmark Study on the Transferability of Graph Self-Supervised Learning
Yu Song, Zhigang Hua, Yan Xie +3
Self-supervised learning (SSL) has shown great promise in graph representation learning. However, most existing graph SSL methods are developed and evaluated under a single-dataset…
A Scalable Pretraining Framework for Link Prediction with Efficient Adaptation
Yu Song, Zhigang Hua, Harry Shomer +4
Link Prediction (LP) is a critical task in graph machine learning. While Graph Neural Networks (GNNs) have significantly advanced LP performance recently, existing methods face key…
Higher-order Structure Boosts Link Prediction on Temporal Graphs
Jingzhe Liu, Zhigang Hua, Yan Xie +5
Temporal Graph Neural Networks (TGNNs) have gained growing attention for modeling and predicting structures in temporal graphs. However, existing TGNNs primarily focus on pairwise…
Unveiling Mode Connectivity in Graph Neural Networks
Bingheng Li, Zhikai Chen, Haoyu Han +3
A fundamental challenge in understanding graph neural networks (GNNs) lies in characterizing their optimization dynamics and loss landscape geometry, critical for improving interpr…
One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs
Jingzhe Liu, Haitao Mao, Zhikai Chen +6
Graph Neural Networks (GNNs) have emerged as a powerful tool to capture intricate network patterns, achieving success across different domains. However, existing GNNs require caref…
Do Neural Scaling Laws Exist on Graph Self-Supervised Learning?
Qian Ma, Haitao Mao, Jingzhe Liu +5
Self-supervised learning~(SSL) is essential to obtain foundation models in NLP and CV domains via effectively leveraging knowledge in large-scale unlabeled data. The reason for its…
A Pure Transformer Pretraining Framework on Text-attributed Graphs
Yu Song, Haitao Mao, Jiachen Xiao +6
Pretraining plays a pivotal role in acquiring generalized knowledge from large-scale data, achieving remarkable successes as evidenced by large models in CV and NLP. However, progr…
Text-space Graph Foundation Models: Comprehensive Benchmarks and New Insights
Zhikai Chen, Haitao Mao, Jingzhe Liu +8
Given the ubiquity of graph data and its applications in diverse domains, building a Graph Foundation Model (GFM) that can work well across different graphs and tasks with a unifie…
Towards Neural Scaling Laws on Graphs
Jingzhe Liu, Haitao Mao, Zhikai Chen +3
Deep graph models (e.g., graph neural networks and graph transformers) have become important techniques for leveraging knowledge across various types of graphs. Yet, the neural sca…