Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks117 from public data
- Hierarchical adaptive deep convolution neural network and its application to bearing fault diagnosis782
A novel hierarchical learning rate adaptive deep convolution neural network based on an improved algorithm that is well suited to the fault-diagnosis model and superior to other existing methods is proposed.
- Graph Neural Networks for Natural Language Processing: A Survey410
A new taxonomy of GNNs for NLP is proposed, which systematically organizes existing research of Gnns forNLP along three axes: graph construction, graph representation learning, and graph based encoder-decoder models.
- A Systematic Survey on Deep Generative Models for Graph Generation211
An extensive overview of the literature in the field of deep generative models for graph generation is provided and taxonomies of deep Generative Models for graphs for both unconditional and conditional graph generation are proposed respectively.
- 112
- 89
- 85
- Deep Fault Recognizer: An Integrated Model to Denoise and Extract Features for Fault Diagnosis in Rotating Machinery85
An integrated deep fault recognizer model based on the stacked denoising autoencoder (SDAE) is applied to both denoise random noises in the raw signals and represent fault features in fault pattern diagnosis for both bearing rolling fault and gearbox fault, trained in a greedy layer-wise fashion.
- Single Image Reflection Separation via Component Synergy78
This paper proposes a more general form of the superposition model by introducing a learnable residue term, which can effectively capture residual information during decomposition, guiding the separated layers to be complete.
- Compact Graph Structure Learning via Mutual Information Compression75
This paper theoretically prove that if the authors optimize basic views and final view based on mutual information, and keep their performance on labels simultaneously, the final view will be a minimal sufficient structure, named CoGSL.
- 65
- 62
- 62
- 57
- A hybrid technique based on convolutional neural network and support vector regression for intelligent diagnosis of rotating machinery54
A hybrid technique based on convolutional neural network and support vector regression is proposed, which is used to promote feature extraction capability and multi-class classification in rolling element bearings and gears.
- Controllable Data Generation by Deep Learning: A Review52
This article formally defines controllable deep data generation, proposes a taxonomy on various techniques and summarizes the evaluation metrics in this specific domain, and highlights the promising future directions of controllable deep data generation.
- FraudGT: A Simple, Effective, and Efficient Graph Transformer for Financial Fraud Detection46
FraudGT is introduced, a simple, effective, and efficient graph transformer (GT) model specifically designed for fraud detection in financial transaction graphs that achieves state-of-the-art performance in detecting fraudulent activities while demonstrating high throughput and significantly lower latency compared to existing methods.
- 46
- 46
- Reversible Decoupling Network for Single Image Reflection Removal44
This work proposes a novel architecture called Reversible Decoupling Network (RDNet), which employs a reversible encoder to secure valuable information while flexibly decoupling transmission- and reflection-relevant features during the forward pass, and customize a transmission-rate-aware prompt generator to dynamically calibrate features, further boosting performance.
- Graph Neural Networks: Foundation, Frontiers and Applications43
This tutorial of Graph Neural Networks (GNNs): Foundation, Frontiers and Applications will cover a broad range of topics in graph neural networks, by reviewing and introducing the fundamental concepts and algorithms of GNNs, new research frontiers of Gnns, and broad and emerging applications with GNNS.
- Cognitive and Scalable Technique for Securing IoT Networks Against Malware Epidemics39
A two-pronged approach with malware detection at node-level, and confinement of malware at network-level is proposed, and to scale with ever-increasing network topology sizes, a novel multi-attribute graph translation that can predict the networkTopology and node state information when provided with a snapshot of topology and nodes-level malware infection is introduced.
- 39
- Vision-based Uneven BEV Representation Learning with Polar Rasterization and Surface Estimation38
PolarBEV is proposed for vision-based uneven BEV representation learning, which keeps real-time inference speed on a single 2080Ti GPU, and outperforms other methods for both BEV semantic segmentation and BEV instance segmentation.
- Deep Graph Translation38
A novel graph-translation-generative-adversarial-nets (GT-GAN) model that transforms the source graphs into their target output graphs and significantly outperforms other baseline methods in terms of both effectiveness and scalability.
- 38
- 38
- 34
- Deep Generative Models for Spatial Networks33
A novel objective for joint spatial-network disentanglement from the perspective of information bottleneck as well as a novel optimization algorithm to optimize the intractable objective is proposed to discover the independent and dependent latent factors of spatial and networks.
- 33
- Generating tertiary protein structures via interpretable graph variational autoencoders29
Novel deep generative models that build upon the graph variational autoencoder framework are presented that are able to capture rich, local and distal constraints and additionally compute disentangled latent representations that reveal the impact of individual latent factors.
- Distant-Supervision of Heterogeneous Multitask Learning for Social Event Forecasting With Multilingual Indicators28
A novel model capable of distant-supervision of heterogeneous multitask learning (DHML) for multilingual spatial social event forecasting, which maps the multilingual heterogeneous features into several latent semantic spaces and then enforces a similar sparsity pattern across them all, using distant supervision across all the languages involved.
- 28
- 27
- Invited: Automated Code generation for Information Technology Tasks in YAML through Large Language Models26
Ansible Wisdom, a natural-language to Ansible YAML code generation tool, aimed at improving IT automation productivity is presented, showing that Ansible Wisdom can accurately generate Ansible script from natural language prompts with performance comparable or better than existing state of the art code generation models.
- 25
- 23
- 20
- Integrating Formal Schedulability Analysis into a Verified OS Kernel20
This paper connects together Prosa, a verified schedulability analyzer, and RT-CertiKOS, averified single-core sequential real-time OS kernel, and shows that it is realistic to connect two completely independent formal developments in a proof assistant.
- 19
- Intelligent Online Selling Point Extraction for E-commerce Recommendation18
The experience developing and deploying the Intelligent Online Selling Point Extraction (IOSPE) system to serve the recommendation system in the JD.com e-commerce platform is reported, thereby significantly scaling up the selling point creation operation and saving human labour.
- 17
- 17
- Interpretable Molecule Generation via Disentanglement Learning17
This paper proposes a generic framework for interpretable molecule generation based on novel disentangled deep graph generative models with property control based on disentanglement enhancement strategy for graphs and proposes new deep neural architecture to achieve this learning objective.
- 17
- Deep-learning-based biomarker of spinal cartilage endplate health using ultra-short echo time magnetic resonance imaging16
The trained deep learning models enable accurate, automated CEP segmentations and T2* biomarker computations that are statistically similar to those from manual segmentations that address limitations with inefficiency and subjectivity associated with manual methods.
- 16
- Small molecule generation via disentangled representation learning16
This work builds on recent work by us and others on deep graph generative frameworks, which capture atomic interactions via a graph-based representation of a small molecule via the graph variational autoencoder framework both to generate biologically-relevant small molecules and to enhance model interpretability.
- 13
- 13
- 12
- Automatic Controllable Product Copywriting for E-Commerce12
The experience in deploying an E-commerce Prefix-based Controllable Copywriting Generation (EPCCG) system into the JD.com e-commerce product recommendation platform is reported and experiments are conducted to validate the effectiveness of the proposed EPCCG.
- 12
- 12
- 12
- 11
- 11
- 11
- 11
- 11
- Bearing Fault Diagnosis Using Convolution Neural Network and Support Vector Regression11
The presented method is used to classify the bearing fault patterns and obtains better results than that of the convolutional neural network and support vector regression machine separately.
- 10
- 10
- 9
- 9
- 9
- 9
- Vague Preference Policy Learning for Conversational Recommendation8
A novel scenario called Vague Preference Multi-Round Conversational Recommendation (VPMCR), which employs a soft estimation mechanism to assign non-zero confidence scores to all candidate items, accommodating users’ vague and dynamic preferences while mitigating over-filtering and setting a new benchmark for CRS research.
- Local Event Forecasting and Synthesis Using Unpaired Deep Graph Translations6
This work proposes an approach for learn the translation of graphs from source-mode to target- mode such that the generated target-mode is indistinguishable from the distribution of the real target- Mode using an adversarial loss.
- 5
- 5
- Deep graph transformation for attributed, directed, and signed networks5
A spectral graph regularization based on the nonparametric graph Laplacian is designed and a novel framework coherently accommodating both node and edge translations is proposed, proven to be a generalization of existing topology translation models.
- The Sixth International Workshop on Deep Learning on Graphs - Methods and Applications (DLG-KDD'21)5
This international workshop on "Deep Learning on Graphs: Method and Applications (DLG-KDD'21)" aims to bring together both academic researchers and industrial practitioners from different backgrounds and perspectives to the above challenges.
- 5
- LIME-Eval: Rethinking Low-light Image Enhancement Evaluation via Object Detection4
LIME-Bench is proposed, the first online benchmark platform designed to collect human preferences for low-light enhancement, providing a valuable dataset for validating the correlation between human perception and automated evaluation metrics.
- User Simulator Assisted Open-ended Conversational Recommendation System4
A User Simulator (US) that communicates with the CRS using natural language based on given user preferences, enabling long-term reinforcement learning and a framework that uses reinforcement learning with two novel rewards, i.e., recommendation and conversation rewards, to train the C RS.
- Pruning Before Training May Improve Generalization, Provably3
This work considers a classification task for overparameterized two-layer neural networks, where the network is randomly pruned according to different rates at the initialization, and shows that as long as the pruning fraction is below a certain threshold, gradient descent can drive the training loss toward zero and the network exhibits good generalization performance.
- 3
- RAPTA: A Hierarchical Representation Learning Solution For Real-Time Prediction of Path-Based Static Timing Analysis3
This is the first work, in which Bidirectional Long Short-Term Memory (Bi-LSTM) representation learning is used to digest raw information for feature engineering, where generation of latent features and Multilayer Perceptron (MLP) based regression for timing prediction can be trained end-to-end.
- 3
- 3
- 3
- Semi-Supervised Semantic Segmentation via Derivative Label Propagation2
A semi-supervised framework, namely DerProp, equipped with a novel derivative label propagation to rectify imperfect pseudo-labels, which effectively alleviates the ill-posed problem that identical similarities correspond to different features through constraining the solution space.
- Efficient Task Offloading Using Ant Colony Optimization and Reptile Search Algorithms in Edge Computing for Things Context2
A novel hybrid metaheuristic algorithm called ACO-RSA, which synergizes two metaheuristic algorithms, Ant Colony Optimization (ACO) and Reptile Search Algorithm (RSA), is introduced, which exhibits robustness and scalability when optimizing task offloading in IoT edge computing environments.
- Deep Learning on Graphs: Methods and Applications (DLG-KDD2023)2
This international workshop on "Deep Learning on Graphs: Method and Applications (DLG-KDD'23)" aims to bring together both academic researchers and industrial practitioners from different backgrounds and perspectives to above challenges.
- 2
- 2
- 2
- 2
- Self-Supervised Cloud Classification with Patch Rotation Tasks (SSCC-PR)1
A self-supervised cloud classification method based on patch rotation prediction that outperforms existing supervised and self-supervised baselines by a clear margin, especially in data-scarce scenarios is proposed.
- A Robust and Adaptive Service Recommendation Framework for Distinct Behavioral Services in Dynamic Multi-Cloud Environments1
A behavior-aware recommendation framework that explicitly integrates DBS characteristics is proposed, and a Markov-based scoring model is designed to propagate compatibility scores across the invocation topology, enabling infrequently invoked services to obtain nonzero scores during early iterations.
- PEdger++: Practical Edge Detection via Assembling Cross Information1
PEdger++ is proposed, a collaborative learning framework designed to reduce computational costs and model sizes while improving edge detection accuracy, and the core principle is that cross-information derived from heterogeneous architectures, diverse training moments, and multiple parameter samplings, is beneficial to enhance learning from an ensemble perspective.
- Research on Decoupling Control Method for Feedwater System of Steam Generator in Nuclear Power Plant1
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- –
- Efficient Deep Generative Models for Spatial Networks via Spanning Tree Sampler–
A Spatial-Network Disentangled Variational Autoencoder (SND-VAE) is proposed to discover the independent and dependent latent factors of spatial and networks and an efficient version SND-VAE-light is proposed, which is based on a novel Efficient Spatial-Network Message Passing Neural Network (ES-MPNN).
- Set Pivot Learning: Redefining Generalized Segmentation with Vision Foundation Models–
This paper introduces the concept of Set Pivot Learning, a paradigm shift that redefines domain generalization (DG) based on Vision Foundation Models (VFMs), and proposes Set Pivot Learning (SPL), a new definition of domain migration task based on VFMs which is more suitable for current research and application requirements.
- –
- –
- –
- –
- –
- –
- Follow-Up Study On Physical And Neurodevelopmental Outcomes In Extremely Preterm Infants At The Corrected Age Of 12 Months–
Early catch-up growth was beneficial for neurodevelopment and close developmental surveillance is of great significance in improving the long-term quality of life of EPIS.
- Mixed mode of instruction database principles and applications–
A student-centered teaching mode is introduced, that is, students are changed from passive recipients to active learners and knowledge internalization is deepened, which not only improves students’ learning initiative, but also strengthens the communication between students and teachers, thus effectively improving teaching efficiency.
- –
- –
- –
- Analysis of link traffic load-based channel assignment for multi-radio mesh network–
A centralized channel allocation optimization framework which considers the traffic load of each link to effectively reducing the overall network interference and increase network throughput is formulated.
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-15. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.