Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleAugust 2024JUST ACCEPTED
Potamoi: Accelerating Neural Rendering via a Unified Streaming Architecture
ACM Transactions on Architecture and Code Optimization (TACO), Just Accepted https://doi.org/10.1145/3689340Neural Radiance Field (NeRF) has emerged as a promising alternative for photorealistic rendering. Despite recent algorithmic advancements, achieving real-time performance on today’s resource-constrained devices remains challenging. In this paper, we ...
- review-articleJuly 2024
A survey of recent methods for addressing AI fairness and bias in biomedicine
Journal of Biomedical Informatics (JOBI), Volume 154, Issue CJun 2024https://doi.org/10.1016/j.jbi.2024.104646Graphical abstractDisplay Omitted
Abstract ObjectivesArtificial intelligence (AI) systems have the potential to revolutionize clinical practices, including improving diagnostic accuracy and surgical decision-making, while also reducing costs and manpower. However, it is important to ...
- research-articleJuly 2024
A novel train–bridge interaction computational framework based on a meshless box girder model
Advances in Engineering Software (ADES), Volume 192, Issue CJun 2024https://doi.org/10.1016/j.advengsoft.2024.103628AbstractIn traditional train–bridge coupled system (TBCS), simply supported box girder bridges are often modeled using Euler beam elements, neglecting their spatial structure. This simplification may yield inaccurate results, impacting the running safety ...
Highlights- A new meshless model is proposed for box girder bridge and other box structures.
- This is the first time that the FSDT-RPIM computational scheme has been integrated into high-speed railway field.
- The proposed novel model can provide ...
- research-articleApril 2024
FaaSMem: Improving Memory Efficiency of Serverless Computing with Memory Pool Architecture
- Chuhao Xu,
- Yiyu Liu,
- Zijun Li,
- Quan Chen,
- Han Zhao,
- Deze Zeng,
- Qian Peng,
- Xueqi Wu,
- Haifeng Zhao,
- Senbo Fu,
- Minyi Guo
ASPLOS '24: Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 3April 2024, Pages 331–348https://doi.org/10.1145/3620666.3651355In serverless computing, an idle container is not recycled directly, in order to mitigate time-consuming cold container startup. These idle containers still occupy the memory, exasperating the memory shortage of today's data centers. By offloading their ...
- research-articleApril 2024
Study on defect detection of metal castings based on supervised enhancement and attention distillation
Machine Vision and Applications (MVAA), Volume 35, Issue 3May 2024https://doi.org/10.1007/s00138-024-01536-0AbstractMetal castings are essential parts and their quality greatly impacts the product’s performance. Current techniques for identifying surface defects in metal castings usually suffer from issues like inadequate accuracy in defect recognition. In ...
-
- research-articleMay 2024
Safety analysis of high-speed trains on bridges under earthquakes using a LSTM-RNN-based surrogate model
- Han Zhao,
- Biao Wei,
- Peng Zhang,
- Peidong Guo,
- Zhanjun Shao,
- Shipeng Xu,
- Lizhong Jiang,
- Huifang Hu,
- Yingying Zeng,
- Ping Xiang
Computers and Structures (CSTR), Volume 294, Issue CApr 2024https://doi.org/10.1016/j.compstruc.2024.107274Highlights- New method predicts seismic response of train-bridge coupled system using deep learning.
- Customized architecture, hyperparameters, and training strategies enhance the surrogate model of the train bridge system.
- This deep learning ...
In this paper, a novel method is proposed to predict the nonlinear seismic response of train-bridge coupled (TBC) systems by utilizing a long short-term memory (LSTM) recurrent neural network (RNN) based surrogate model. The surrogate model ...
- research-articleJune 2024
Adaptive fuzzy sliding mode control of uncertain nonholonomic wheeled mobile robot with external disturbance and actuator saturation
Information Sciences: an International Journal (ISCI), Volume 663, Issue CMar 2024https://doi.org/10.1016/j.ins.2024.120303AbstractThis paper developed a modified barrier function-based adaptive sliding mode control (MBFASMC) method to improve the tracking precision and robustness performance of the nonholonomic wheeled mobile robot (NWMR), which is subject to actuator ...
Highlights- The finite-time control with predefined precision for nonholonomic wheeled mobile robot with actuator saturation is achieved.
- The proposed method eliminates the requirements for saturation level and guarantees the non-overestimation ...
- research-articleJanuary 2024
Parameter-Agnostic Deep Graph Clustering
ACM Transactions on Knowledge Discovery from Data (TKDD), Volume 18, Issue 3Article No.: 66, Pages 1–20https://doi.org/10.1145/3633783Deep graph clustering, efficiently dividing nodes into multiple disjoint clusters in an unsupervised manner, has become a crucial tool for analyzing ubiquitous graph data. Existing methods have acquired impressive clustering effects by optimizing the ...
- research-articleMay 2024
Cooperative working performance of a dual-arm robot system optimised by a neural network adaptive preset control
International Journal of Sensor Networks (IJSNET), Volume 45, Issue 12024, Pages 54–65https://doi.org/10.1504/ijsnet.2024.138753This paper innovatively integrates preset performance control technology with adaptive neural network control targeting a dual-arm robot system with nonlinear uncertainties, developing a strategy demonstrating exceptional control performance under ...
- research-articleMay 2024
Learning list-level domain-invariant representations for ranking
- Ruicheng Xian,
- Honglei Zhuang,
- Zhen Qin,
- Hamed Zamani,
- Jing Lu,
- Ji Ma,
- Kai Hui,
- Han Zhao,
- Xuanhui Wang,
- Michael Bendersky
NIPS '23: Proceedings of the 37th International Conference on Neural Information Processing SystemsDecember 2023, Article No.: 2824, Pages 64695–64724Domain adaptation aims to transfer the knowledge learned on (data-rich) source domains to (low-resource) target domains, and a popular method is invariant representation learning, which matches and aligns the data distributions on the feature space. ...
- research-articleMay 2024
Efficient learning of linear graph neural networks via node subsampling
NIPS '23: Proceedings of the 37th International Conference on Neural Information Processing SystemsDecember 2023, Article No.: 2422, Pages 55479–55501Graph Neural Networks (GNNs) are a powerful class of machine learning models with applications in recommender systems, drug discovery, social network analysis, and computer vision. One challenge with their implementation is that GNNs often take large-...
- research-articleMay 2024
Revisiting scalarization in multi-task learning: a theoretical perspective
NIPS '23: Proceedings of the 37th International Conference on Neural Information Processing SystemsDecember 2023, Article No.: 2106, Pages 48510–48533Linear scalarization, i.e., combining all loss functions by a weighted sum, has been the default choice in the literature of multi-task learning (MTL) since its inception. In recent years, there is a surge of interest in developing Specialized Multi-Task ...
- research-articleOctober 2023
Maximizing the Utilization of GPUs Used by Cloud Gaming through Adaptive Co-location with Combo
SoCC '23: Proceedings of the 2023 ACM Symposium on Cloud ComputingOctober 2023, Pages 265–280https://doi.org/10.1145/3620678.3624660Cloud vendors are now providing cloud gaming services with GPUs. GPUs in cloud gaming experience periods of idle because not every frame in a game always keeps the GPU busy for rendering. Previous works temporally co-locate games with best-effort ...
- research-articleSeptember 2023
Snow depth retrieval using GPS signal-to-noise ratio data based on improved complete ensemble empirical mode decomposition
AbstractSnow is essential to the Earth's water source and plays a significant role in studying the climate system and hydrological cycle. Snow depth monitoring has recently become an application of Global Navigation Satellite System (GNSS) instruments. ...
- ArticleSeptember 2023
Train Your Own GNN Teacher: Graph-Aware Distillation on Textual Graphs
- Costas Mavromatis,
- Vassilis N. Ioannidis,
- Shen Wang,
- Da Zheng,
- Soji Adeshina,
- Jun Ma,
- Han Zhao,
- Christos Faloutsos,
- George Karypis
Machine Learning and Knowledge Discovery in Databases: Research TrackSep 2023, Pages 157–173https://doi.org/10.1007/978-3-031-43418-1_10AbstractHow can we learn effective node representations on textual graphs? Graph Neural Networks (GNNs) that use Language Models (LMs) to encode textual information of graphs achieve state-of-the-art performance in many node classification tasks. Yet, ...
- research-articleAugust 2023
Improving Cluster Utilization Through Adaptive Resource Management for Deep Neural Network and CPU Jobs Colocation
IEEE Transactions on Computers (ITCO), Volume 72, Issue 12Dec. 2023, Pages 3458–3472https://doi.org/10.1109/TC.2023.3303988While deep neural network (DNN) models are mainly trained using GPUs, many companies and research institutions build shared GPU clusters. These clusters host DNN training jobs, DNN inference jobs, and CPU jobs (jobs in traditional areas). DNN training ...
- research-articleJuly 2023
Game-Theoretic Optimization Toward Diffeomorphism-Based Robust Control of Fuzzy Dynamical Systems With State and Input Constraints
IEEE Transactions on Fuzzy Systems (TOFS), Volume 32, Issue 2Feb. 2024, Pages 373–387https://doi.org/10.1109/TFUZZ.2023.3298341This work investigates a game-theoretic optimization approach toward robust control of uncertain dynamical systems with state and input constraints. The uncertainty involved is possibly rapidly time-varying but bounded within a prescribed fuzzy set. For ...
- research-articleJuly 2023
Fair and optimal classification via post-processing
ICML'23: Proceedings of the 40th International Conference on Machine LearningJuly 2023, Article No.: 1581, Pages 37977–38012To mitigate the bias exhibited by machine learning models, fairness criteria can be integrated into the training process to ensure fair treatment across all demographics, but it often comes at the expense of model performance. Understanding such tradeoffs,...
- research-articleJuly 2023
Structural re-weighting improves graph domain adaptation
ICML'23: Proceedings of the 40th International Conference on Machine LearningJuly 2023, Article No.: 901, Pages 21778–21793In many real-world applications, graph-structured data used for training and testing have differences in distribution, such as in high energy physics (HEP) where simulation data used for training may not match real experiments. Graph domain adaptation (...
- research-articleJuly 2023
Understanding the impact of adversarial robustness on accuracy disparity
ICML'23: Proceedings of the 40th International Conference on Machine LearningJuly 2023, Article No.: 556, Pages 13679–13709While it has long been empirically observed that adversarial robustness may be at odds with standard accuracy and may have further disparate impacts on different classes, it remains an open question to what extent such observations hold and how the class ...