Publications

Research output

Papers and preprints on graph algorithms, graph learning, and data-centric AI.

† alphabetical author order · * equal contribution

Preview figure for Scalable Graph Kernel Query with Error Guarantees

PVLDB2026

Scalable Graph Kernel Query with Error Guarantees

Changan Liu*, Haoyu Liu*, Siqiang Luo, Laks V. S. Lakshmanan

Preview figure for Near-Optimality for Single-Source Personalized PageRank

PODS 2026Best Newcomer Research Paper Award, SIGMOD/PODS 2026

Near-Optimality for Single-Source Personalized PageRank

Haoyu Liu† with Xinpeng Jiang†, Siqiang Luo†, and Xiaokui Xiao†

Preview figure for When Deepfake Detection Meets Graph Neural Network: A Unified and Lightweight Learning Framework

KDD 2026

When Deepfake Detection Meets Graph Neural Network: A Unified and Lightweight Learning Framework

Haoyu Liu*, Chaoyu Gong*, Mengke He, Jiate Li, Kai Han, Siqiang Luo

Details PDF arXiv Code Artifacts

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

SIGMOD2026PREMIA Best Student Paper Award 2025 in Singapore

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

Ningyi Liao, Haoyu Liu, Zulun Zhu, Siqiang Luo, Laks V. S. Lakshmanan

Details PDF arXiv Code DOI

Preview figure for SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation

ICDE 2025

SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation

Haoyu Liu, Ningyi Liao, Siqiang Luo

Details arXiv Paper Slides

Preview figure for Right Answer at the Right Time: Temporal Retrieval-Augmented Generation via Graph Summarization

arXiv preprint2025

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

Zulun Zhu, Haoyu Liu, Mengke He, Siqiang Luo

Preview figure for BIRD: Efficient Approximation of Bidirectional Hidden Personalized PageRank

PVLDB 2024

BIRD: Efficient Approximation of Bidirectional Hidden Personalized PageRank

Haoyu Liu, Siqiang Luo

Details Paper Code DOI

Preview figure for Topology-Monitorable Contrastive Learning on Dynamic Graphs

KDD 2024

Topology-Monitorable Contrastive Learning on Dynamic Graphs

Zulun Zhu, Kai Wang, Haoyu Liu, Jintang Li, Siqiang Luo

Details Paper DOI

Preview figure for Exploring Coarse-grained Pre-guided Attention to Assist Fine-grained Attention Reinforcement Learning Agents

IJCNN 2022

Exploring Coarse-grained Pre-guided Attention to Assist Fine-grained Attention Reinforcement Learning Agents

Haoyu Liu, Yang Liu, Xingrui Wang, Hanfang Yang

Preview figure for LEBP - Language Expectation & Binding Policy: A Two-Stream Framework for Embodied Vision-and-Language Interaction Task Learning Agents

3rd in CVPR ALFRED Challenge, 2022

LEBP - Language Expectation & Binding Policy: A Two-Stream Framework for Embodied Vision-and-Language Interaction Task Learning Agents

Haoyu Liu, Yang Liu, Hongkai He, Hanfang Yang

Preview figure for Nightlight as a Proxy of Economic Indicators: Fine-grained GDP Inference around Chinese Mainland via Attention-augmented CNN from Daytime Satellite Imagery

Remote Sensing2020

Nightlight as a Proxy of Economic Indicators: Fine-grained GDP Inference around Chinese Mainland via Attention-augmented CNN from Daytime Satellite Imagery

Haoyu Liu, Xianwen He, Yanbing Bai, Xing Liu, Yilin Wu, Yanyun Zhao, Hanfang Yang

Preview figure for Pyramid Pooling Module-based Semi-Siamese Network: A Benchmark Model for Assessing Building Damage from xBD Satellite Imagery Datasets

Remote Sensing2020

Pyramid Pooling Module-based Semi-Siamese Network: A Benchmark Model for Assessing Building Damage from xBD Satellite Imagery Datasets

Yanbing Bai, Junjie Hu, Jinhua Su, Xing Liu, Haoyu Liu, Xianwen He, Shengwang Meng, Erick Mas, Shunichi Koshimura