94 citations · 394 across the 15 of their papers we have counts for
15 papers
Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems
Xuan Zhang, Limei Wang, Jacob Helwig +60
Advances in artificial intelligence (AI) are fueling a new paradigm of discoveries in natural sciences. Today, AI has started to advance natural sciences by improving, accelerating…
QH9: A Quantum Hamiltonian Prediction Benchmark for QM9 Molecules
Haiyang Yu, Meng Liu, Youzhi Luo +4
Supervised machine learning approaches have been increasingly used in accelerating electronic structure prediction as surrogates of first-principle computational methods, such as d…
Efficient and Equivariant Graph Networks for Predicting Quantum Hamiltonian
Haiyang Yu, Zhao Xu, Xiaofeng Qian +2
We consider the prediction of the Hamiltonian matrix, which finds use in quantum chemistry and condensed matter physics. Efficiency and equivariance are two important, but conflict…
GraphFM: Improving Large-Scale GNN Training via Feature Momentum
Haiyang Yu, Limei Wang, Bokun Wang +3
Training of graph neural networks (GNNs) for large-scale node classification is challenging. A key difficulty lies in obtaining accurate hidden node representations while avoiding…
Alexa Teacher Model: Pretraining and Distilling Multi-Billion-Parameter Encoders for Natural Language Understanding Systems
Jack FitzGerald, Shankar Ananthakrishnan, Konstantine Arkoudas +38
We present results from a large-scale experiment on pretraining encoders with non-embedding parameter counts ranging from 700M to 9.3B, their subsequent distillation into smaller m…
Empowering GNNs via Edge-Aware Weisfeiler-Leman Algorithm
Meng Liu, Haiyang Yu, Shuiwang Ji
Message passing graph neural networks (GNNs) are known to have their expressiveness upper-bounded by 1-dimensional Weisfeiler-Leman (1-WL) algorithm. To achieve more powerful GNNs,…
DeepKE: A Deep Learning Based Knowledge Extraction Toolkit for Knowledge Base Population
Ningyu Zhang, Xin Xu, Liankuan Tao +19
We present an open-source and extensible knowledge extraction toolkit DeepKE, supporting complicated low-resource, document-level and multimodal scenarios in the knowledge base pop…
Text Gestalt: Stroke-Aware Scene Text Image Super-Resolution
Jingye Chen, Haiyang Yu, Jianqi Ma +2
In the last decade, the blossom of deep learning has witnessed the rapid development of scene text recognition. However, the recognition of low-resolution scene text images remains…
Benchmarking Chinese Text Recognition: Datasets, Baselines, and an Empirical Study
Haiyang Yu, Jingye Chen, Bin Li +6
The flourishing blossom of deep learning has witnessed the rapid development of text recognition in recent years. However, the existing text recognition methods are mainly proposed…
Interventional Aspect-Based Sentiment Analysis
Zhen Bi, Ningyu Zhang, Ganqiang Ye +3
Recent neural-based aspect-based sentiment analysis approaches, though achieving promising improvement on benchmark datasets, have reported suffering from poor robustness when enco…
DIG: A Turnkey Library for Diving into Graph Deep Learning Research
Meng Liu, Youzhi Luo, Limei Wang +13
Although there exist several libraries for deep learning on graphs, they are aiming at implementing basic operations for graph deep learning. In the research community, implementin…
On Explainability of Graph Neural Networks via Subgraph Explorations
Hao Yuan, Haiyang Yu, Jie Wang +2
We consider the problem of explaining the predictions of graph neural networks (GNNs), which otherwise are considered as black boxes. Existing methods invariably focus on explainin…
Explainability in Graph Neural Networks: A Taxonomic Survey
Hao Yuan, Haiyang Yu, Shurui Gui +1
Deep learning methods are achieving ever-increasing performance on many artificial intelligence tasks. A major limitation of deep models is that they are not amenable to interpreta…
Bridging Text and Knowledge with Multi-Prototype Embedding for Few-Shot Relational Triple Extraction
Haiyang Yu, Ningyu Zhang, Shumin Deng +3
Current supervised relational triple extraction approaches require huge amounts of labeled data and thus suffer from poor performance in few-shot settings. However, people can gras…
The Devil is the Classifier: Investigating Long Tail Relation Classification with Decoupling Analysis
Haiyang Yu, Ningyu Zhang, Shumin Deng +3
Long-tailed relation classification is a challenging problem as the head classes may dominate the training phase, thereby leading to the deterioration of the tail performance. Exis…