activity
20222026
most citedSpiking Graph Convolutional Networks

7 citations · 20 across the 9 of their papers we have counts for

collaborators

10 papers

cs.LG2026

Coden: Efficient Temporal Graph Neural Networks for Continuous Prediction

Zulun Zhu, Siqiang Luo

Temporal Graph Neural Networks (TGNNs) are pivotal in processing dynamic graphs. However, existing TGNNs primarily target one-time predictions for a given temporal span, whereas ma…

cs.IR2025

Right Answer at the Right Time - Temporal Retrieval-Augmented Generation via Graph Summarization

Zulun Zhu, Haoyu Liu, Mengke He +1

Question answering in temporal knowledge graphs requires retrieval that is both time-consistent and efficient. Existing RAG methods are largely semantic and typically neglect expli…

cs.IR2025★ 1 cited

Graph-based Approaches and Functionalities in Retrieval-Augmented Generation: A Comprehensive Survey

Zulun Zhu, Tiancheng Huang, Kai Wang +3

Large language models (LLMs) struggle with the factual error during inference due to the lack of sufficient training data and the most updated knowledge, leading to the hallucinati…

cs.LG2024

Revisiting Graph Autoencoders as Implicit Contrastive Learners

Jintang Li, Ruofan Wu, Yuchang Zhu +3

Graph autoencoders (GAEs) and graph contrastive learning (GCL) are two major paradigms for self-supervised representation learning on graphs, yet they are often studied in isolatio…

cs.LG2024★ 4 cited

A Comprehensive Benchmark on Spectral GNNs: The Impact on Efficiency, Memory, and Effectiveness

Ningyi Liao, Haoyu Liu, Zulun Zhu +2

With recent advancements in graph neural networks (GNNs), spectral GNNs have received increasing popularity by virtue of their ability to retrieve graph signals in the spectral dom…

cs.NE2023★ 5 cited

A Graph is Worth 1-bit Spikes: When Graph Contrastive Learning Meets Spiking Neural Networks

Jintang Li, Huizhe Zhang, Ruofan Wu +5

While contrastive self-supervised learning has become the de-facto learning paradigm for graph neural networks, the pursuit of higher task accuracy requires a larger hidden dimensi…