Huidong Liang — accepted AI-conference papers

2026

Towards Quantifying Long-Range Interactions in Graph Machine Learning: a Large Graph Dataset and a Measurement

Huidong Liang, Haitz Sáez de Ocáriz Borde, Baskaran Sripathmanathan, Michael M. Bronstein, Xiaowen Dong

ICLR 2026poster

Long-range dependencies are critical for effective graph representation learning, yet most existing datasets focus on small graphs tailored to inductive tasks, offering limited insight into long-range interactions. Current evaluations primarily compare models employing global attention (e.g., graph…

Cited by 0 Source ↗code ↗Scholar ↗

2024

Bayesian Optimization of Functions over Node Subsets in Graphs

Huidong Liang, Xingchen Wan, Xiaowen Dong

NeurIPS 2024poster

We address the problem of optimizing over functions defined on node subsets in a graph. The optimization of such functions is often a non-trivial task given their combinatorial, black-box and expensive-to-evaluate nature. Although various algorithms have been introduced in the literature, most are…

Cited by 2 Source ↗PDF ↗code ↗Scholar ↗

2023

Bytecover3: Accurate Cover Song Identification On Short Queries

Xingjian Du, Zijie Wang, Xia Liang, Huidong Liang, Bilei Zhu, Zejun Ma

ICASSP 2023accepted

Deep learning based methods have become a paradigm for cover song identification (CSI) in recent years, where the ByteCover systems have achieved state-of-the-art results on all the mainstream datasets of CSI. However, with the burgeon of short videos, many real-world applications require matching s…

Cited by 0 Source ↗Scholar ↗

2022

How Neural Processes Improve Graph Link Prediction

Huidong Liang, Junbin Gao

ICASSP 2022accepted

We propose a meta-learning approach with graph neural networks for link prediction: Neural Processes for Graph Neural Networks (NPGNN), which can not only perform both transductive and inductive learning tasks, but also generalize well when only training on a small subgraph. The key idea is to assum…

Cited by 0 Source ↗Scholar ↗