Author name cluster

Guodong Li

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.

12 papers

2 author rows

EAAI Journal 2026 Journal Article

QFTD: An efficient quantum federated learning for transformer fault diagnosis with minimal gated unit in smart grid

Guodong Li
Junjie Luo
Qingle Wang
Lin Liu
Chunyan Wei
Huawei Wang
Zhichao Zhang

Quantum federated learning (QFL), as an emerging quantum algorithm, has been initially applied in fields such as healthcare and intelligent transportation. It can achieve efficient model training while protecting the privacy of power data. It is an excellent solution for addressing the challenges of data decentralization and privacy in fault diagnosis. To further enhance the generalization and efficiency of QFL, we propose an efficient quantum federated learning algorithm for power transformer fault diagnosis with the minimal gated unit (QFTD) in the smart grid, which is an initial application of QFL to power transformer fault diagnosis in the smart grid. We integrate a quantum orthogonal convolutional neural network with the classical minimal gated unit, forming a quantum minimal gated orthogonal convolutional neural network (QMOCNN) as the local model of QFTD. By adding the quantum orthogonal layer to the quantum convolutional neural network, the generalization ability and stability of the model improve. Experimental results demonstrate that QMOCNN achieves an accuracy of 99. 48% in power transformer fault diagnosis within the smart grid, exhibiting superior convergence speed and classification accuracy compared to other methods. After introducing the federated learning framework, the QFTD can also achieve an accuracy of 95. 83%. The experiment on the three types of quantum circuit noise proves that QFTD has good performance in noise resistance. Our work represents a significant exploration and advancement in applying quantum algorithms within the realm of fault diagnosis in power systems.

Details DOI

EAAI Journal 2025 Journal Article

A novel facial expression recognition method based on cross direction attention network

Cheng Peng
Guodong Li
Likang Lin
Bowen Zhang
Kun Zou
Sio Long Lo
Ah Chung Tsoi

Facial expression recognition (FER) is an area of growing interest in computer vision research. This paper extends the framework provided by the ‘Distract your Attention Network’ (DAN) which consists of multiple parallel branches, each branch composes of a spatial attention (SA) module followed by a channel attention (CA) module, and then these multiple branches are fused together before being passed into a classifier module. The spatial attention module of DAN has an internal channel dimension of 1, while our proposed Cross Directional Attention Network (CDAN)-I and CDAN-II contain respectively an internal channel dimension of 512 (same as the channel dimension of the input), and internal channel dimension of 1024 (double that of the channel dimension of the input). These increases in internal channel dimension allow extraction of more features, before they are being made to conform with the input channel dimension. Despite these seemingly simple modifications from that of DAN, both CDAN-I and CDAN-II are found to outperform those of DAN, a state-of-the-art FER method, on four popular FER benchmark datasets: RAF-DB (Real world Affective Face-database), AffectNet-7 (AffectNet with Seven Categories) AffectNet-8 ( AffectNet with Eight Categories), and CK+ (Cohn–Kanada Extended). Moreover, we make use of three statistical indexes for clustering analysis, and verified that the CDAN-I and CDAN-II modules have been able to increase the inter-cluster distances, and decrease the intra-cluster distances, when compared with those obtained by the backbone ResNet-18 network (Residual Network with 18 Layers), thus providing a quantitative analysis technique in this area.

Details DOI

ICLR Conference 2025 Conference Paper

From Layers to States: A State Space Model Perspective to Deep Neural Network Layer Dynamics

Qinshuo Liu
Weiqin Zhao
Wei Huang
Yanwen Fang
Lequan Yu
Guodong Li

The depth of neural networks is a critical factor for their capability, with deeper models often demonstrating superior performance. Motivated by this, significant efforts have been made to enhance layer aggregation - reusing information from previous layers to better extract features at the current layer, to improve the representational power of deep neural networks. However, previous works have primarily addressed this problem from a discrete-state perspective which is not suitable as the number of network layers grows. This paper novelly treats the outputs from layers as states of a continuous process and considers leveraging the state space model (SSM) to design the aggregation of layers in very deep neural networks. Moreover, inspired by its advancements in modeling long sequences, the Selective State Space Models (S6) is employed to design a new module called Selective State Space Model Layer Aggregation (S6LA). This module aims to combine traditional CNN or transformer architectures within a sequential framework, enhancing the representational capabilities of state-of-the-art vision networks. Extensive experiments show that S6LA delivers substantial improvements in both image classification and detection tasks, highlighting the potential of integrating SSMs with contemporary deep learning techniques.

Details

JBHI Journal 2025 Journal Article

Knowledge Graph Neural Network With Spatial-Aware Capsule for Drug-Drug Interaction Prediction

Xiaorui Su
Bowei Zhao
Guodong Li
Jun Zhang
Pengwei Hu
Zhuhong You
Lun Hu

Uncovering novel drug-drug interactions (DDIs) plays a pivotal role in advancing drug development and improving clinical treatment. The outstanding effectiveness of graph neural networks (GNNs) has garnered significant interest in the field of DDI prediction. Consequently, there has been a notable surge in the development of network-based computational approaches for predicting DDIs. However, current approaches face limitations in capturing the spatial relationships between neighboring nodes and their higher-level features during the aggregation of neighbor representations. To address this issue, this study introduces a novel model, KGCNN, designed to comprehensively tackle DDI prediction tasks by considering spatial relationships between molecules within the biomedical knowledge graph (BKG). KGCNN is built upon a message-passing GNN framework, consisting of propagation and aggregation. In the context of the BKG, KGCNN governs the propagation of information based on semantic relationships, which determine the flow and exchange of information between different molecules. In contrast to traditional linear aggregators, KGCNN introduces a spatial-aware capsule aggregator, which effectively captures the spatial relationships among neighboring molecules and their higher-level features within the graph structure. The ultimate goal is to leverage these learned drug representations to predict potential DDIs. To evaluate the effectiveness of KGCNN, it undergoes testing on two datasets. Extensive experimental results demonstrate its superiority in DDI predictions and quantified performance.

Details DOI

JBHI Journal 2024 Journal Article

Discovering Consensus Regions for Interpretable Identification of RNA N6-Methyladenosine Modification Sites via Graph Contrastive Clustering

Guodong Li
Bowei Zhao
Xiaorui Su
Yue Yang
Pengwei Hu
Xi Zhou
Lun Hu

As a pivotal post-transcriptional modification of RNA, N6-methyladenosine (m6A) has a substantial influence on gene expression modulation and cellular fate determination. Although a variety of computational models have been developed to accurately identify potential m6A modification sites, few of them are capable of interpreting the identification process with insights gained from consensus knowledge. To overcome this problem, we propose a deep learning model, namely M6A-DCR, by discovering consensus regions for interpretable identification of m6A modification sites. In particular, M6A-DCR first constructs an instance graph for each RNA sequence by integrating specific positions and types of nucleotides. The discovery of consensus regions is then formulated as a graph clustering problem in light of aggregating all instance graphs. After that, M6A-DCR adopts a motif-aware graph reconstruction optimization process to learn high-quality embeddings of input RNA sequences, thus achieving the identification of m6A modification sites in an end-to-end manner. Experimental results demonstrate the superior performance of M6A-DCR by comparing it with several state-of-the-art identification models. The consideration of consensus regions empowers our model to make interpretable predictions at the motif level. The analysis of cross validation through different species and tissues further verifies the consistency between the identification results of M6A-DCR and the evolutionary relationships among species.

Details DOI

ICLR Conference 2023 Conference Paper

Cross-Layer Retrospective Retrieving via Layer Attention

Yanwen Fang
Yuxi Cai
Jintai Chen
Jingyu Zhao 0001
Guangjian Tian
Guodong Li

More and more evidence has shown that strengthening layer interactions can enhance the representation power of a deep neural network, while self-attention excels at learning interdependencies by retrieving query-activated information. Motivated by this, we devise a cross-layer attention mechanism, called multi-head recurrent layer attention (MRLA), that sends a query representation of the current layer to all previous layers to retrieve query-related information from different levels of receptive fields. A light-weighted version of MRLA is also proposed to reduce the quadratic computation cost. The proposed layer attention mechanism can enrich the representation power of many state-of-the-art vision networks, including CNNs and vision transformers. Its effectiveness has been extensively evaluated in image classification, object detection and instance segmentation tasks, where improvements can be consistently observed. For example, our MRLA can improve 1.6% Top-1 accuracy on ResNet-50, while only introducing 0.16M parameters and 0.07B FLOPs. Surprisingly, it can boost the performances by a large margin of 3-4% box AP and mask AP in dense prediction tasks. Our code is available at https://github.com/joyfang1106/MRLA.

Details

ICLR Conference 2023 Conference Paper

Encoding Recurrence into Transformers

Feiqing Huang
Kexin Lu
Yuxi Cai
Zhen Qin
Yanwen Fang
Guangjian Tian
Guodong Li

This paper novelly breaks down with ignorable loss an RNN layer into a sequence of simple RNNs, each of which can be further rewritten into a lightweight positional encoding matrix of a self-attention, named the Recurrence Encoding Matrix (REM). Thus, recurrent dynamics introduced by the RNN layer can be encapsulated into the positional encodings of a multihead self-attention, and this makes it possible to seamlessly incorporate these recurrent dynamics into a Transformer, leading to a new module, Self-Attention with Recurrence (RSA). The proposed module can leverage the recurrent inductive bias of REMs to achieve a better sample efficiency than its corresponding baseline Transformer, while the self-attention is used to model the remaining non-recurrent signals. The relative proportions of these two components are controlled by a data-driven gated mechanism, and the effectiveness of RSA modules are demonstrated by four sequential learning tasks.

Details

NeurIPS Conference 2021 Conference Paper

Recurrence along Depth: Deep Convolutional Neural Networks with Recurrent Layer Aggregation

Jingyu Zhao
Yanwen Fang
Guodong Li

This paper introduces a concept of layer aggregation to describe how information from previous layers can be reused to better extract features at the current layer. While DenseNet is a typical example of the layer aggregation mechanism, its redundancy has been commonly criticized in the literature. This motivates us to propose a very light-weighted module, called recurrent layer aggregation (RLA), by making use of the sequential structure of layers in a deep CNN. Our RLA module is compatible with many mainstream deep CNNs, including ResNets, Xception and MobileNetV2, and its effectiveness is verified by our extensive experiments on image classification, object detection and instance segmentation tasks. Specifically, improvements can be uniformly observed on CIFAR, ImageNet and MS COCO datasets, and the corresponding RLA-Nets can surprisingly boost the performances by 2-3% on the object detection task. This evidences the power of our RLA module in helping main CNNs better learn structural information in images.

PDF Details

AAAI Conference 2020 Conference Paper

Compact Autoregressive Network

Di Wang
Feiqing Huang
Jingyu Zhao
Guodong Li
Guangjian Tian

Autoregressive networks can achieve promising performance in many sequence modeling tasks with short-range dependence. However, when handling high-dimensional inputs and outputs, the massive amount of parameters in the network leads to expensive computational cost and low learning efﬁciency. The problem can be alleviated slightly by introducing one more narrow hidden layer to the network, but the sample size required to achieve a certain training error is still substantial. To address this challenge, we rearrange the weight matrices of a linear autoregressive network into a tensor form, and then make use of Tucker decomposition to represent lowrank structures. This leads to a novel compact autoregressive network, called Tucker AutoRegressive (TAR) net. Interestingly, the TAR net can be applied to sequences with longrange dependence since the dimension along the sequential order is reduced. Theoretical studies show that the TAR net improves the learning efﬁciency, and requires much fewer samples for model training. Experiments on synthetic and real-world datasets demonstrate the promising performance of the proposed compact network.

PDF Details

ICML Conference 2020 Conference Paper

Do RNN and LSTM have Long Memory?

Jingyu Zhao 0001
Feiqing Huang
Jia Lv
Yanjie Duan
Zhen Qin
Guodong Li
Guangjian Tian

The LSTM network was proposed to overcome the difficulty in learning long-term dependence, and has made significant advancements in applications. With its success and drawbacks in mind, this paper raises the question - do RNN and LSTM have long memory? We answer it partially by proving that RNN and LSTM do not have long memory from a statistical perspective. A new definition for long memory networks is further introduced, and it requires the model weights to decay at a polynomial rate. To verify our theory, we convert RNN and LSTM into long memory networks by making a minimal modification, and their superiority is illustrated in modeling long-term dependence of various datasets.

Details

IJCAI Conference 2019 Conference Paper

Ensemble-based Ultrahigh-dimensional Variable Screening

Wei Tu
Dong Yang
Linglong Kong
Menglu Che
Qian Shi
Guodong Li
Guangjian Tian

Since the sure independence screening (SIS) method by Fan and Lv, many different variable screening methods have been proposed based on different measures under different models. However, most of these methods are designed for specific models. In practice, we often have very little information about the data generating process and different methods can result in very different sets of features. The heterogeneity presented here motivates us to combine various screening methods simultaneously. In this paper, we introduce a general ensemble-based framework to efficiently combine results from multiple variable screening methods. The consistency and sure screening property of proposed framework has been established. Extensive simulation studies confirm our intuition that the proposed ensemble-based method is more robust against model specification than using single variable screening method. The proposed ensemble-based method is used to predict attention deficit hyperactivity disorder (ADHD) status using brain function connectivity (FC).

PDF Details

LPAR Conference 2005 Conference Paper

Functional Correctness Proofs of Encryption Algorithms

Jianjun Duan
Joe Hurd
Guodong Li
Scott Owens
Konrad Slind
Junxing Zhang

Abstract We discuss a collection of mechanized formal proofs of symmetric key block encryption algorithms (AES, MARS, Twofish, RC6, Serpent, IDEA, and TEA), performed in an implementation of higher order logic. For each algorithm, functional correctness, namely that decryption inverts encryption, is formally proved by a simple but effective proof methodology involving application of invertibility lemmas in the course of symbolic evaluation. Block ciphers are then lifted to the encryption of arbitrary datatypes by using modes of operation to encrypt lists of bits produced by a polytypic encoding method.

Details