Author name cluster

Limei Wang

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

10 papers

2 author rows

EAAI Journal 2026 Journal Article

Online multi-channel real-time detection method and device for surface defects of winter jujube based on improved faster regions with convolutional neural networks model

Zeyang Xin
Weihui Wang
Limei Wang
Qinglun Che
Jianjun Zhang

To overcome the limitations of low precision, inefficiency, and high labor cost in traditional winter jujube sorting, this study proposes a dual innovation integrating algorithmic enhancement and multi-channel hardware design. Firstly, an improved Faster Region with Convolutional Neural Network (Faster R-CNN) is developed, in which the original Visual Geometry Group 16-layer network (VGG16) backbone is replaced by Residual Network-50 (ResNet50) combined with a Squeeze-and-Excitation (SE) attention module and a Feature Pyramid Network (FPN) to enhance adaptive multi-scale feature learning. In addition, the conventional Non-Maximum Suppression (NMS) is substituted with a lightweight Soft-NMS variant to mitigate false suppression in overlapping detection regions. These algorithmic refinements collectively improve defect discrimination accuracy and robustness, achieving a mean Average Precision (mAP) of 91. 60 % and a detection speed of 17. 5 frames per second (FPS). Compared to Single Shot MultiBox Detector (SSD), Detection Transformer (DETR), You Only Look Once version 8-n (YOLOv8-n), and YOLOv11-s, mAP improved by 14 %, 9. 5 %, 12. 2 %, and 5. 94 %, respectively. Ultimately, the optimized model was deployed on a customized eight-channel intelligent sorting device. The integrated system can process approximately 480 fruits per minute, achieving classification accuracy exceeding 93 % for all defect categories. This research offers new insights for intelligent sorting in the winter jujube industry and provides valuable reference for sorting other small and medium-sized fruits.

Details DOI

ICML Conference 2025 Conference Paper

Geometry Informed Tokenization of Molecules for Language Model Generation

Xiner Li
Limei Wang
Youzhi Luo
Carl Edwards
Shurui Gui
Yuchao Lin
Heng Ji 0001
Shuiwang Ji

We consider molecule generation in 3D space using language models (LMs), which requires discrete tokenization of 3D molecular geometries. Although tokenization of molecular graphs exists, that for 3D geometries is largely unexplored. Here, we attempt to bridge this gap by proposing a novel method which converts molecular geometries into SE(3)-invariant 1D discrete sequences. Our method consists of canonical labeling and invariant spherical representation steps, which together maintain geometric and atomic fidelity in a format conducive to LMs. Our experiments show that, when coupled with our proposed method, various LMs excel in molecular geometry generation, especially in controlled generation tasks. Our code has been released as part of the AIRS library (https: //github. com/divelab/AIRS/).

Details

ICLR Conference 2025 Conference Paper

Learning Graph Quantized Tokenizers

Limei Wang
Kaveh Hassani
Si Zhang
Dongqi Fu
Baichuan Yuan
Weilin Cong
Zhigang Hua
Hao Wu

Transformers serve as the backbone architectures of Foundational Models, where domain-specific tokenizers allow them to adapt to various domains. Graph Transformers (GTs) have recently emerged as leading models in geometric deep learning, outperforming Graph Neural Networks (GNNs) in various graph learning tasks. However, the development of tokenizers for graphs has lagged behind other modalities, with existing approaches relying on heuristics or GNNs co-trained with Transformers. To address this, we introduce GQT (\textbf{G}raph \textbf{Q}uantized \textbf{T}okenizer), which decouples tokenizer training from Transformer training by leveraging multi-task graph self-supervised learning, yielding robust and generalizable graph tokens. Furthermore, the GQT utilizes Residual Vector Quantization (RVQ) to learn hierarchical discrete tokens, resulting in significantly reduced memory requirements and improved generalization capabilities. By combining the GQT with token modulation, a Transformer encoder achieves state-of-the-art performance on 20 out of 22 benchmarks, including large-scale homophilic and heterophilic datasets. The implementation is publicly available at \href{https://github.com/limei0307/GQT}{https://github.com/limei0307/GQT}.

Details

NeurIPS Conference 2023 Conference Paper

A new perspective on building efficient and expressive 3D equivariant graph neural networks

Weitao Du
Yuanqi Du
Limei Wang
Dieqiao Feng
Guifeng Wang
Shuiwang Ji
Carla P. Gomes
Zhi-Ming Ma

Geometric deep learning enables the encoding of physical symmetries in modeling 3D objects. Despite rapid progress in encoding 3D symmetries into Graph Neural Networks (GNNs), a comprehensive evaluation of the expressiveness of these network architectures through a local-to-global analysis lacks today. In this paper, we propose a local hierarchy of 3D isomorphism to evaluate the expressive power of equivariant GNNs and investigate the process of representing global geometric information from local patches. Our work leads to two crucial modules for designing expressive and efficient geometric GNNs; namely local substructure encoding (\textbf{LSE}) and frame transition encoding (\textbf{FTE}). To demonstrate the applicability of our theory, we propose LEFTNet which effectively implements these modules and achieves state-of-the-art performance on both scalar-valued and vector-valued molecular property prediction tasks. We further point out future design space for 3D equivariant graph neural networks. Our codes are available at \url{https: //github. com/yuanqidu/LeftNet}.

PDF Details

ICLR Conference 2023 Conference Paper

Learning Hierarchical Protein Representations via Complete 3D Graph Networks

Limei Wang
Haoran Liu
Yi Liu 0059
Jerry Kurtin
Shuiwang Ji

We consider representation learning for proteins with 3D structures. We build 3D graphs based on protein structures and develop graph networks to learn their representations. Depending on the levels of details that we wish to capture, protein representations can be computed at different levels, \emph{e.g.}, the amino acid, backbone, or all-atom levels. Importantly, there exist hierarchical relations among different levels. In this work, we propose to develop a novel hierarchical graph network, known as ProNet, to capture the relations. Our ProNet is very flexible and can be used to compute protein representations at different levels of granularity. By treating each amino acid as a node in graph modeling as well as harnessing the inherent hierarchies, our ProNet is more effective and efficient than existing methods. We also show that, given a base 3D graph network that is complete, our ProNet representations are also complete at all levels. Experimental results show that ProNet outperforms recent methods on most datasets. In addition, results indicate that different downstream tasks may require representations at different levels. Our code is publicly available as part of the DIG library (\url{https://github.com/divelab/DIG}).

Details

NeurIPS Conference 2022 Conference Paper

ComENet: Towards Complete and Efficient Message Passing for 3D Molecular Graphs

Limei Wang
Yi Liu
Yuchao Lin
Haoran Liu
Shuiwang Ji

Many real-world data can be modeled as 3D graphs, but learning representations that incorporates 3D information completely and efficiently is challenging. Existing methods either use partial 3D information, or suffer from excessive computational cost. To incorporate 3D information completely and efficiently, we propose a novel message passing scheme that operates within 1-hop neighborhood. Our method guarantees full completeness of 3D information on 3D graphs by achieving global and local completeness. Notably, we propose the important rotation angles to fulfill global completeness. Additionally, we show that our method is orders of magnitude faster than prior methods. We provide rigorous proof of completeness and analysis of time complexity for our methods. As molecules are in essence quantum systems, we build the \underline{com}plete and \underline{e}fficient graph neural network (ComENet) by combing quantum inspired basis functions and the proposed message passing scheme. Experimental results demonstrate the capability and efficiency of ComENet, especially on real-world datasets that are large in both numbers and sizes of graphs. Our code is publicly available as part of the DIG library (\url{https: //github. com/divelab/DIG}).

PDF Details

NeurIPS Conference 2022 Conference Paper

GOOD: A Graph Out-of-Distribution Benchmark

Shurui Gui
Xiner Li
Limei Wang
Shuiwang Ji

Out-of-distribution (OOD) learning deals with scenarios in which training and test data follow different distributions. Although general OOD problems have been intensively studied in machine learning, graph OOD is only an emerging area of research. Currently, there lacks a systematic benchmark tailored to graph OOD method evaluation. In this work, we aim at developing an OOD benchmark, known as GOOD, for graphs specifically. We explicitly make distinctions between covariate and concept shifts and design data splits that accurately reflect different shifts. We consider both graph and node prediction tasks as there are key differences in designing shifts. Overall, GOOD contains 11 datasets with 17 domain selections. When combined with covariate, concept, and no shifts, we obtain 51 different splits. We provide performance results on 10 commonly used baseline methods with 10 random runs. This results in 510 dataset-model combinations in total. Our results show significant performance gaps between in-distribution and OOD settings. Our results also shed light on different performance trends between covariate and concept shifts by different methods. Our GOOD benchmark is a growing project and expects to expand in both quantity and variety of resources as the area develops. The GOOD benchmark can be accessed via https: //github. com/divelab/GOOD/.

PDF Details

ICML Conference 2022 Conference Paper

GraphFM: Improving Large-Scale GNN Training via Feature Momentum

Haiyang Yu 0005
Limei Wang
Bokun Wang
Meng Liu 0015
Tianbao Yang
Shuiwang Ji

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 the neighborhood explosion problem. Here, we propose a new technique, named feature momentum (FM), that uses a momentum step to incorporate historical embeddings when updating feature representations. We develop two specific algorithms, known as GraphFM-IB and GraphFM-OB, that consider in-batch and out-of-batch data, respectively. GraphFM-IB applies FM to in-batch sampled data, while GraphFM-OB applies FM to out-of-batch data that are 1-hop neighborhood of in-batch data. We provide a convergence analysis for GraphFM-IB and some theoretical insight for GraphFM-OB. Empirically, we observe that GraphFM-IB can effectively alleviate the neighborhood explosion problem of existing methods. In addition, GraphFM-OB achieves promising performance on multiple large-scale graph datasets.

Details

ICLR Conference 2022 Conference Paper

Spherical Message Passing for 3D Molecular Graphs

Yi Liu 0059
Limei Wang
Meng Liu 0015
Yuchao Lin
Xuan Zhang
Bora Oztekin
Shuiwang Ji

We consider representation learning of 3D molecular graphs in which each atom is associated with a spatial position in 3D. This is an under-explored area of research, and a principled message passing framework is currently lacking. In this work, we conduct analyses in the spherical coordinate system (SCS) for the complete identification of 3D graph structures. Based on such observations, we propose the spherical message passing (SMP) as a novel and powerful scheme for 3D molecular learning. SMP dramatically reduces training complexity, enabling it to perform efficiently on large-scale molecules. In addition, SMP is capable of distinguishing almost all molecular structures, and the uncovered cases may not exist in practice. Based on meaningful physically-based representations of 3D information, we further propose the SphereNet for 3D molecular learning. Experimental results demonstrate that the use of meaningful 3D information in SphereNet leads to significant performance improvements in prediction tasks. Our results also demonstrate the advantages of SphereNet in terms of capability, efficiency, and scalability.

Details

JMLR Journal 2021 Journal Article

DIG: A Turnkey Library for Diving into Graph Deep Learning Research

Meng Liu
Youzhi Luo
Limei Wang
Yaochen Xie
Hao Yuan
Shurui Gui
Haiyang Yu
Zhao Xu

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, implementing and benchmarking various advanced tasks are still painful and time-consuming with existing libraries. To facilitate graph deep learning research, we introduce DIG: Dive into Graphs, a turnkey library that provides a unified testbed for higher level, research-oriented graph deep learning tasks. Currently, we consider graph generation, self-supervised learning on graphs, explainability of graph neural networks, and deep learning on 3D graphs. For each direction, we provide unified implementations of data interfaces, common algorithms, and evaluation metrics. Altogether, DIG is an extensible, open-source, and turnkey library for researchers to develop new methods and effortlessly compare with common baselines using widely used datasets and evaluation metrics. Source code is available at https://github.com/divelab/DIG. [abs] [ pdf ][ bib ] [ code ] &copy JMLR 2021. ( edit, beta )

PDF Details