Author name cluster

Chong Chen

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.

17 papers

2 author rows

EAAI Journal 2026 Journal Article

A collaborative approach based on large language model and knowledge graphs for information integration towards smart manufacturing

Ruihao Li
Chong Chen
Ying Liu
Tao Wang
Haidong Shao
Lianglun Cheng

In the era of smart manufacturing, integrating vast amounts of information has become an essential task. Knowledge Graph (KG) is a key technology for improving information integration, which can greatly improve the performance of question-answering for Large Language Models (LLMs). However, the existing approach mainly adopts KG as the plug-in database for Retrieval-Augmented Generation (RAG), which cannot achieve accurate answering due to the imperfections of KG. In order to address this challenge, a collaborative LLM-KG framework is proposed to iteratively update the KG, which can provide fine-grained knowledge for RAG. The methodology firstly constructs a foundational ontology, and adopts LLM for knowledge triples extraction to establish an initial KG based on multi-source data. Then, competency questions (CQs) are designed for the evaluation and optimization of the initial KG. After ontology optimization, a fine-grained KG is obtained to facilitate a robust question-answering mechanism through RAG. The proposed iterative approach can effectively refine the system's decision-support capabilities. An experimental study based on the real-world shipbuilding process data is implemented. The experimental results demonstrate that the answering accuracy can be improved from 86.18% to 93.09% with the enhancement of the proposed approach.

Details DOI

TIST Journal 2025 Journal Article

A GPT-assisted Multi-Granularity Contrastive Learning approach for Knowledge Graph Entity Typing

Hongbin Zhang
Tao Wang
Zhuowei Wang
Nankai Lin
Chong Chen
Lianglun Cheng

Knowledge graph entity typing (KGET) is an efficient way to infer possible missing types for entities, which has become a key instrument to enhance the construction of knowledge graphs (KGs). Existing models to KGET have mainly focused on a single granularity information such as distinct entity information, but other granularity information including entity-to-type-clusters, the same cluster and interaction information have not been fully explored, resulting in inferring incorrect types in KGs. To address this, we propose a GPT-assisted Multi-Granularity Contrastive Learning (GMGCL) approach to acquire entity-to-type-clusters, entity, type-cluster and relation information by GPT-assisted entity-to-type-clusters clustering, entity-based, cluster-based and relation-based contrastive learning, respectively. Our approach is evaluated on FB15kET and YAGO43kET datasets, outperforming other baselines and obtaining a 1.35% average improvement at least on MRR.

Details DOI

EAAI Journal 2025 Journal Article

A survey of semantic extraction for speech semantic communications: Metrics, approaches, perspectives and challenges

Chong Chen
Linyu Huang

With the rapid development of communication technology, traditional bit transmission can no longer meet the demands of emerging intelligent applications for real-time communication, low latency, and efficient transmission. As a new communication paradigm, Semantic communication (SemCom) focuses on understanding and transmitting task-relevant semantic information, making it an important direction for improving communication efficiency. Researchers have extensively studied SemCom for text and images, but the research on speech is relatively limited. Semantic extraction is a key component of SemCom, and it varies significantly across modalities. Machine learning and deep learning techniques have significantly advanced speech signal processing and semantic extraction tasks, including speech embedding and automatic speech recognition, thus enhancing end-to-end speech SemCom networks. This paper provides a survey of the research progress in semantic extraction for speech SemCom. First, the paper describes the fundamentals of SemCom and speech signal processing, including acoustic feature and speech preprocessing. Taking into account the differences in the evaluation metrics between SemCom and traditional communication, this paper then presents the semantic metrics proposed in existing studies. Next, this paper compares recent progress in speech embedding and two commonly used methods for semantic extraction from speech: one based on speech-to-text conversion and the other on direct extraction from speech signals. Assistive methods for pragmatic-level semantic extraction are also discussed. Subsequently, existing studies on speech SemCom are reviewed and compared. Finally, we discuss the challenges and future directions in SemCom, with the aim of providing references for future research.

Details DOI

AAAI Conference 2025 Conference Paper

DREAM: Decoupled Discriminative Learning with Bigraph-aware Alignment for Semi-supervised 2D-3D Cross-modal Retrieval

Fan Zhang
Changhu Wang
Zebang Cheng
Xiaojiang Peng
Dongjie Wang
Yijia Xiao
Chong Chen
Xian-Sheng Hua

With the burst of big data, 2D-3D cross-modal retrieval has received increasing attention, which aims to retrieve relevant data from one modality given the query from the other modality. In this paper, we study an underexplored yet practical problem of semi-supervised 2D-3D cross-modal retrieval, which could suffer from serious label scarcity in real-world applications. Moreover, the huge heterogeneous gap could deteriorate the process of learning from unlabeled data. In this work, we propose a novel approach named Decoupled Discriminative Learning with Bigraph-aware Alignment (DREAM) for semi-supervised 2D-3D cross-modal retrieval. The core of our DREAM is to decouple the label prediction and reliability measurement processes to reduce overconfident samples in discriminative learning. In particular, we enhance a label prediction module with label propagation from labeled samples and additionally introduce a reliability measurement module to learn the scores of predicted labels. To reduce class-related bias, we compare reliability scores with class-specific adaptive thresholds to identify samples for additional learning. In addition, negative labels are estimated for unselected samples, which guides soft semantic learning to make the best use of all the information. To further minimize the heterogeneous gap, we build a bigraph graph that connects cross-modal similar examples and then conduct learning to cluster with most edges kept for alignment. Extensive experiments on several benchmark datasets validate the superiority of the proposed DREAM.

PDF Details DOI

AAAI Conference 2025 Conference Paper

SongSong: A Time Phonograph for Chinese SongCi Music from Thousand of Years Away

Jiliang Hu
Jiajia Li
Ziyi Pan
Chong Chen
Zuchao Li
Ping Wang
Lefei Zhang

Recently, there have been significant advancements in music generation. However, existing models primarily focus on creating modern pop songs, making it challenging to produce ancient music with distinct rhythms and styles, such as ancient Chinese SongCi. In this paper, we introduce SongSong, the first music generation model capable of restoring Chinese SongCi to our knowledge. Our model first predicts the melody from the input SongCi, then separately generates the singing voice and accompaniment based on that melody, and finally combines all elements to create the final piece of music. Additionally, to address the lack of ancient music datasets, we create OpenSongSong, a comprehensive dataset of ancient Chinese SongCi music, featuring 29.9 hours of compositions by various renowned SongCi music masters. To assess SongSong's proficiency in performing SongCi, we randomly select 85 SongCi sentences that were not part of the training set for evaluation against SongSong and music generation platforms such as Suno and SkyMusic. The subjective and objective outcomes indicate that our proposed model achieves leading performance in generating high-quality SongCi music.

PDF Details DOI

EAAI Journal 2024 Journal Article

Boosting efficient attention assisted cyclic adversarial auto-encoder for rotating component fault diagnosis under low label rates

Jianguo Miao
Zihao Deng
Congying Deng
Chong Chen

In practical engineering scenarios with limited labeled samples, conventional semi-supervised diagnostic methods face challenges in achieving satisfactory identification outcomes. To address the aforementioned issues, this paper introduces an incremental semi-supervised learning (ISL) approach based on boosting efficient attention (BEA) assisted cyclic adversarial auto-encoder (CAAE), referred to as BEA-CAAE. The CAAE enhances unsupervised feature representation by simultaneously constraining the distribution of encoded features and aligning elements of the reconstructed samples through a cyclic encoding strategy. The BEA improves classical attention weights' activation strength to better capture vital information, thereby boosting the feature extraction capabilities of both CAAE and the classifier. The ISL employs a stepwise pseudo-label propagation strategy to incrementally filter high-confidence samples, enhancing sample and label utilization, and improving diagnostic accuracy under low label rate conditions. Experiments conducted on multiple test rigs with simple structures as well as large-scale rotating components test rigs that mimic real-world engineering conditions have demonstrated that the proposed method exhibits a significant advantage over existing semi-supervised fault diagnosis approaches in terms of fault diagnosis accuracy and generalization capability, especially under low label rate conditions.

Details DOI

EAAI Journal 2024 Journal Article

Compact convolutional transformers- generative adversarial network for compound fault diagnosis of industrial robot

Chong Chen
Tao Wang
Kaijie Lu
Ying Liu
Lianglun Cheng

The safe operation of Industrial robots is a major concern in intelligent manufacturing. Accurate compound fault diagnosis is essential to the safe operation of industrial robots, while it is challenging to achieve since the compound fault samples are hard to be collected. Generative adversarial network (GAN) is a useful tool for addressing the data imbalance issue. However, the computation efficiency of GAN in addressing the data imbalance issue has not been investigated. Hence, this study proposes a lightweight GAN named compact convolutional Transformers-GAN (CCT-GAN) to alleviate the data imbalance issue in compound fault diagnosis modelling. Firstly, the feedback current signals collected from the industrial robot are transformed into time-frequency images via continuous wavelet transformation (CWT). Secondly, CCT-GAN is designed to achieve high-quality fake data generation and compound fault diagnosis modelling without large computational costs. Thirdly, the relation between a single fault and the compound fault is considered in the compound fault diagnosis modelling via multi-hot representation to alleviate the data imbalance issue. An experimental study based on the real-world compound fault dataset of industrial robots reveals that the proposed CCT-GAN shows merits in compound fault diagnosis modelling in comparison with the prevailing algorithms. The results indicate that CCT-GAN can performance of compound fault diagnosis when only 100 data samples from each compound fault category are available.

Details DOI

EAAI Journal 2024 Journal Article

Deep learning approach for accurate and stable recognition of driver's lateral intentions using naturalistic driving data

Kun Cheng
Dongye Sun
Datong Qin
Chong Chen

Accurate and stable recognition of a driver's lateral intention is a crucial prerequisite for the proper functioning of advanced driver-assistance systems (ADAS). Existing studies usually rely on auxiliary sensor signals, such as cameras and eye trackers; however, this reliance poses challenges in applying these methods to vehicles lacking such auxiliary sensors. Furthermore, existing studies have not fully leveraged the inherent temporal dependence of lateral intentions, leading to difficulties in avoiding erroneous recognition interruptions. Thus, this study proposes a deep-learning-based lateral intention recognition method to achieve accurate and stable recognition of lateral intention using onboard sensor signals. First, a real vehicle is used to collect a vast amount of driving data, and thus guarantee the robustness and practicality of the recognition model. Subsequently, vehicle trajectories are extracted, and a trajectory clustering method is used to label lateral intentions of the driving data; these intention labels and a feature selection algorithm are utilized to select the most representative recognition features. Therefore, a lateral driving intention recognition model is constructed using double convolutional neural networks with a long short-term memory layer (CNN-LSTM). This network architecture can fully utilize the temporal dependence of lateral intentions. Finally, the recognition performance of the designed double CNN-LSTM networks is validated using the existing driving data and real-world vehicle tests. The results indicate that the double CNN-LSTM networks can achieve stable recognition of lateral intention in real-time and the accuracy reaches 98. 64% in the experiment.

Details DOI

NeurIPS Conference 2024 Conference Paper

PURE: Prompt Evolution with Graph ODE for Out-of-distribution Fluid Dynamics Modeling

Hao Wu
Changhu Wang
Fan Xu
Jinbao Xue
Chong Chen
Xian-Sheng Hua
Xiao Luo

This work studies the problem of out-of-distribution fluid dynamics modeling. Previous works usually design effective neural operators to learn from mesh-based data structures. However, in real-world applications, they would suffer from distribution shifts from the variance of system parameters and temporal evolution of the dynamical system. In this paper, we propose a novel approach named \underline{P}rompt Evol\underline{u}tion with G\underline{r}aph OD\underline{E} (\method{}) for out-of-distribution fluid dynamics modeling. The core of our \method{} is to learn time-evolving prompts using a graph ODE to adapt spatio-temporal forecasting models to different scenarios. In particular, our \method{} first learns from historical observations and system parameters in the frequency domain to explore multi-view context information, which could effectively initialize prompt embeddings. More importantly, we incorporate the interpolation of observation sequences into a graph ODE, which can capture the temporal evolution of prompt embeddings for model adaptation. These time-evolving prompt embeddings are then incorporated into basic forecasting models to overcome temporal distribution shifts. We also minimize the mutual information between prompt embeddings and observation embeddings to enhance the robustness of our model to different distributions. Extensive experiments on various benchmark datasets validate the superiority of the proposed \method{} in comparison to various baselines.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Semi-supervised Knowledge Transfer Across Multi-omic Single-cell Data

Fan Zhang
Tianyu Liu
Zihao Chen
Xiaojiang Peng
Chong Chen
Xian-Sheng Hua
Xiao Luo
Hongyu Zhao

Knowledge transfer between multi-omic single-cell data aims to effectively transfer cell types from scRNA-seq data to unannotated scATAC-seq data. Several approaches aim to reduce the heterogeneity of multi-omic data while maintaining the discriminability of cell types with extensive annotated data. However, in reality, the cost of collecting both a large amount of labeled scRNA-seq data and scATAC-seq data is expensive. Therefore, this paper explores a practical yet underexplored problem of knowledge transfer across multi-omic single-cell data under cell type scarcity. To address this problem, we propose a semi-supervised knowledge transfer framework named Dual label scArcity elimiNation with Cross-omic multi-samplE Mixup (DANCE). To overcome the label scarcity in scRNA-seq data, we generate pseudo-labels based on optimal transport and merge them into the labeled scRNA-seq data. Moreover, we adopt a divide-and-conquer strategy which divides the scATAC-seq data into source-like and target-specific data. For source-like samples, we employ consistency regularization with random perturbations while for target-specific samples, we select a few candidate labels and progressively eliminate incorrect cell types from the label set for additional supervision. Next, we generate virtual scRNA-seq samples with multi-sample Mixup based on the class-wise similarity to reduce cell heterogeneity. Extensive experiments on many benchmark datasets suggest the superiority of our DANCE over a series of state-of-the-art methods.

PDF Details DOI

IROS Conference 2023 Conference Paper

A Minimal Collision Strategy of Synergy Between Pushing and Grasping for Large Clusters of Objects

Chong Chen
Shijun Yan
Miaolong Yuan
Chiat-Pin Tay
Dongkyu Choi
Quang Dan Le

Grasping and moving objects in a large cluster is a common real scenario. In such scenarios, tens of objects are adjacent to each other, even stacked layer by layer, so that simple grasp would not work due to obstruction. In this paper, we propose a well-designed strategy to use synergy of pushing and grasping to automatically push and grasp objects in a large tightly packed cluster of objects. Our strategy is to detect and grasp isolated graspable objects first before other actions. We then use a smart strategy that pushes objects at the narrowest edge of the clusters. For push action, the robot pushes the edge at the perpendicular direction relative to the cluster, thus improving the performance of isolation and minimizing collisions. We have conducted experiments in both simulation and real-world environments with more than 20 cluttered objects and demonstrated that our solution outperforms existing deep learning based methods, especially in challenging cases, and achieves significantly higher completion rate, grasp success rate, picked rate and efficiency.

Details

NeurIPS Conference 2023 Conference Paper

IDEA: An Invariant Perspective for Efficient Domain Adaptive Image Retrieval

Haixin Wang
Hao Wu
Jinan Sun
Shikun Zhang
Chong Chen
Xian-Sheng Hua
Xiao Luo

In this paper, we investigate the problem of unsupervised domain adaptive hashing, which leverage knowledge from a label-rich source domain to expedite learning to hash on a label-scarce target domain. Although numerous existing approaches attempt to incorporate transfer learning techniques into deep hashing frameworks, they often neglect the essential invariance for adequate alignment between these two domains. Worse yet, these methods fail to distinguish between causal and non-causal effects embedded in images, rendering cross-domain retrieval ineffective. To address these challenges, we propose an Invariance-acquired Domain AdaptivE HAshing (IDEA) model. Our IDEA first decomposes each image into a causal feature representing label information, and a non-causal feature indicating domain information. Subsequently, we generate discriminative hash codes using causal features with consistency learning on both source and target domains. More importantly, we employ a generative model for synthetic samples to simulate the intervention of various non-causal effects, ultimately minimizing their impact on hash codes for domain invariance. Comprehensive experiments conducted on benchmark datasets validate the superior performance of our IDEA compared to a variety of competitive baselines.

PDF Details

IJCAI Conference 2022 Conference Paper

TGNN: A Joint Semi-supervised Framework for Graph-level Classification

Wei Ju
Xiao Luo
Meng Qu
Yifan Wang
Chong Chen
Minghua Deng
Xian-Sheng Hua
Ming Zhang

This paper studies semi-supervised graph classification, a crucial task with a wide range of applications in social network analysis and bioinformatics. Recent works typically adopt graph neural networks to learn graph-level representations for classification, failing to explicitly leverage features derived from graph topology (e. g. , paths). Moreover, when labeled data is scarce, these methods are far from satisfactory due to their insufficient topology exploration of unlabeled data. We address the challenge by proposing a novel semi-supervised framework called Twin Graph Neural Network (TGNN). To explore graph structural information from complementary views, our TGNN has a message passing module and a graph kernel module. To fully utilize unlabeled data, for each module, we calculate the similarity of each unlabeled graph to other labeled graphs in the memory bank and our consistency loss encourages consistency between two similarity distributions in different embedding spaces. The two twin modules collaborate with each other by exchanging instance similarity knowledge to fully explore the structure information of both labeled and unlabeled data. We evaluate our TGNN on various public datasets and show that it achieves strong performance.

PDF Details DOI

IJCAI Conference 2021 Conference Paper

CIMON: Towards High-quality Hash Codes

Xiao Luo
Daqing Wu
Zeyu Ma
Chong Chen
Minghua Deng
Jinwen Ma
Zhongming Jin
Jianqiang Huang

Recently, hashing is widely used in approximate nearest neighbor search for its storage and computational efficiency. Most of the unsupervised hashing methods learn to map images into semantic similarity-preserving hash codes by constructing local semantic similarity structure from the pre-trained model as the guiding information, i. e. , treating each point pair similar if their distance is small in feature space. However, due to the inefficient representation ability of the pre-trained model, many false positives and negatives in local semantic similarity will be introduced and lead to error propagation during the hash code learning. Moreover, few of the methods consider the robustness of models, which will cause instability of hash codes to disturbance. In this paper, we propose a new method named Comprehensive sImilarity Mining and cOnsistency learNing (CIMON). First, we use global refinement and similarity statistical distribution to obtain reliable and smooth guidance. Second, both semantic and contrastive consistency learning are introduced to derive both disturb-invariant and discriminative hash codes. Extensive experiments on several benchmark datasets show that the proposed method outperforms a wide range of state-of-the-art methods in both retrieval performance and robustness.

PDF Details DOI

AAAI Conference 2021 Conference Paper

Graph Heterogeneous Multi-Relational Recommendation

Chong Chen
Weizhi Ma
Min Zhang
Zhaowei Wang
Xiuqiang He
Chenyang Wang
Yiqun Liu
Shaoping Ma

Traditional studies on recommender systems usually leverage only one type of user behaviors (the optimization target, such as purchase), despite the fact that users also generate a large number of various types of interaction data (e. g. , view, click, add-to-cart, etc). Generally, these heterogeneous multirelational data provide well-structured information and can be used for high-quality recommendation. Early efforts towards leveraging these heterogeneous data fail to capture the high-hop structure of user-item interactions, which are unable to make full use of them and may only achieve constrained recommendation performance. In this work, we propose a new multi-relational recommendation model named Graph Heterogeneous Collaborative Filtering (GHCF). To explore the high-hop heterogeneous user-item interactions, we take the advantages of Graph Convolutional Network (GCN) and further improve it to jointly embed both representations of nodes (users and items) and relations for multi-relational prediction. Moreover, to fully utilize the whole heterogeneous data, we perform the advanced efficient non-sampling optimization under a multi-task learning framework. Experimental results on two public benchmarks show that GHCF significantly outperforms the state-of-the-art recommendation methods, especially for cold-start users who have few primary item interactions. Further analysis verifies the importance of the proposed embedding propagation for modelling high-hop heterogeneous user-item interactions, showing the rationality and effectiveness of GHCF. Our implementation has been released (https: //github. com/chenchongthu/GHCF).

PDF Details

AAAI Conference 2020 Conference Paper

Efficient Heterogeneous Collaborative Filtering without Negative Sampling for Recommendation

Chong Chen
Min Zhang
Yongfeng Zhang
Weizhi Ma
Yiqun Liu
Shaoping Ma

Recent studies on recommendation have largely focused on exploring state-of-the-art neural networks to improve the expressiveness of models, while typically apply the Negative Sampling (NS) strategy for efﬁcient learning. Despite effectiveness, two important issues have not been well-considered in existing methods: 1) NS suffers from dramatic ﬂuctuation, making sampling-based methods difﬁcult to achieve the optimal ranking performance in practical applications; 2) although heterogeneous feedback (e. g. , view, click, and purchase) is widespread in many online systems, most existing methods leverage only one primary type of user feedback such as purchase. In this work, we propose a novel nonsampling transfer learning solution, named Efﬁcient Heterogeneous Collaborative Filtering (EHCF) for Top-N recommendation. It can not only model ﬁne-grained user-item relations, but also efﬁciently learn model parameters from the whole heterogeneous data (including all unlabeled data) with a rather low time complexity. Extensive experiments on three real-world datasets show that EHCF signiﬁcantly outperforms state-of-the-art recommendation methods in both traditional (single-behavior) and heterogeneous scenarios. Moreover, EHCF shows signiﬁcant improvements in training ef- ﬁciency, making it more applicable to real-world large-scale systems. Our implementation has been released 1 to facilitate further developments on efﬁcient whole-data based neural methods.

PDF Details

EAAI Journal 2018 Journal Article

Extracting topic-sensitive content from textual documents—A hybrid topic model approach

Yan Liang
Ying Liu
Chong Chen
Zhigang Jiang

When exploring information of a topic, users often concern its different aspects. For instance, product designers are interested in seeking information of specific topic aspects such as technical challenge and usability from online consumer opinions, while potential buyers wish to obtain general sentiment of public opinions. In this paper, we study an interesting problem called topic-sensitive content extraction (TSCE). TSCE aims to extract contents that are relevant to the samples of topic aspects highlighted by users from a single document in a given text collection. To tackle TSCE, we have proposed a new hybrid topic model which integrates different structures in both topic space and context space. It focuses on identifying contents associated with a specified topic aspect from each document. By modeling gradient documents via term profiles for context modeling and by leveraging local and global differences between probability distributions over words in both topic modeling and context modeling, it has better captured the features of various language patterns. Hence, sentence relevance ranking according to a specific topic aspect is largely improved. The experimental studies on extracting critical contents of specific aspects, including motivation and design solution, from technical patents for design analysis have shown the merits of the proposed modeling.

Details DOI