Chentao Wu
YOU?
Author Swipe
View article: BAPFL: Exploring Backdoor Attacks Against Prototype-based Federated Learning
BAPFL: Exploring Backdoor Attacks Against Prototype-based Federated Learning Open
Prototype-based federated learning (PFL) has emerged as a promising paradigm to address data heterogeneity problems in federated learning, as it leverages mean feature vectors as prototypes to enhance model generalization. However, its rob…
View article: Comprehensive Prediction of Dominant Reservoirs in the Guantao Formation Volcanic Rock Reservoir in NanPu Oilfield
Comprehensive Prediction of Dominant Reservoirs in the Guantao Formation Volcanic Rock Reservoir in NanPu Oilfield Open
The Guantao Formation volcanic rocks are nearly 200m thick in the No. 1 structural belt of Nanpu Sag. The recognition degree of volcanic lithology and rock equality is low. The reservoir characteristics and accumulation rules of volcanic r…
View article: Transmission dynamics of ST346 carbapenem-resistant Providencia huaxiensis carrying blaNDM-1 and/or blaKPC-2 during the COVID-19 pandemic
Transmission dynamics of ST346 carbapenem-resistant Providencia huaxiensis carrying blaNDM-1 and/or blaKPC-2 during the COVID-19 pandemic Open
Carbapenem-resistant Providencia spp. (CRPs) isolates are increasing, posing severe therapeutic challenges. Here, we analyzed 46 CRP isolates carrying bla NDM-1 and/or bla KPC-2 from patients (n = 40) with 60% demonstrating clinical infect…
View article: BLOCKS: Blockchain-supported Cross-Silo Knowledge Sharing for Efficient LLM Services
BLOCKS: Blockchain-supported Cross-Silo Knowledge Sharing for Efficient LLM Services Open
The hallucination problem of Large Language Models (LLMs) has increasingly drawn attention. Augmenting LLMs with external knowledge is a promising solution to address this issue. However, due to privacy and security concerns, a vast amount…
View article: PS-WL: A Probability-Sensitive Wear Leveling scheme for SSD array scaling
PS-WL: A Probability-Sensitive Wear Leveling scheme for SSD array scaling Open
As flash-based Solid State Drive (SSD) arrays become essential to modern data centers, scaling these arrays to meet explosive data growth is a frequent and critical operation. However, the conventional wear-leveling (WL) paradigm applied d…
View article: STREAMINGGS: Voxel-Based Streaming 3D Gaussian Splatting with Memory Optimization and Architectural Support
STREAMINGGS: Voxel-Based Streaming 3D Gaussian Splatting with Memory Optimization and Architectural Support Open
3D Gaussian Splatting (3DGS) has gained popularity for its efficiency and sparse Gaussian-based representation. However, 3DGS struggles to meet the real-time requirement of 90 frames per second (FPS) on resource-constrained mobile devices,…
View article: LOVO: Efficient Complex Object Query in Large-Scale Video Datasets
LOVO: Efficient Complex Object Query in Large-Scale Video Datasets Open
The widespread deployment of cameras has led to an exponential increase in video data, creating vast opportunities for applications such as traffic management and crime surveillance. However, querying specific objects from large-scale vide…
View article: Interactive Mechanism Optimization Design Based on GeoGebra
Interactive Mechanism Optimization Design Based on GeoGebra Open
To address the phenomenon of cumbersome solving of the parameters of the law of motion of the mechanism and the difficulty of verifying the feasibility of the motion in the traditional mechanism design process, this paper proposes to use t…
View article: Gaze into the Pattern: Characterizing Spatial Patterns with Internal Temporal Correlations for Hardware Prefetching
Gaze into the Pattern: Characterizing Spatial Patterns with Internal Temporal Correlations for Hardware Prefetching Open
Hardware prefetching is one of the most widely-used techniques for hiding long data access latency. To address the challenges faced by hardware prefetching, architects have proposed to detect and exploit the spatial locality at the granula…
View article: HMT: A Hybrid Mitigating and Transferring Approach on I/O Throughput Degradation for Erasure Coded Storage Systems
HMT: A Hybrid Mitigating and Transferring Approach on I/O Throughput Degradation for Erasure Coded Storage Systems Open
In cloud storage systems with erasure coding (EC), increased demand for data services and EC-based data recovery lead to high volumes of concurrent I/O requests, potentially causing network congestion or server overload. Network congestion…
View article: LocalGCL: Local-aware Contrastive Learning for Graphs
LocalGCL: Local-aware Contrastive Learning for Graphs Open
Graph representation learning (GRL) makes considerable progress recently, which encodes graphs with topological structures into low-dimensional embeddings. Meanwhile, the time-consuming and costly process of annotating graph labels manuall…
View article: SecureCut: Federated Gradient Boosting Decision Trees with Efficient Machine Unlearning
SecureCut: Federated Gradient Boosting Decision Trees with Efficient Machine Unlearning Open
In response to legislation mandating companies to honor the \textit{right to be forgotten} by erasing user data, it has become imperative to enable data removal in Vertical Federated Learning (VFL) where multiple parties provide private fe…
View article: A Hierarchical Framework for Quadruped Robots Gait Planning Based on DDPG
A Hierarchical Framework for Quadruped Robots Gait Planning Based on DDPG Open
In recent years, significant progress has been made in employing reinforcement learning for controlling legged robots. However, a major challenge arises with quadruped robots due to their continuous states and vast action space, making opt…
View article: MARS: Exploiting Multi-Level Parallelism for DNN Workloads on Adaptive Multi-Accelerator Systems
MARS: Exploiting Multi-Level Parallelism for DNN Workloads on Adaptive Multi-Accelerator Systems Open
Along with the fast evolution of deep neural networks, the hardware system is also developing rapidly. As a promising solution achieving high scalability and low manufacturing cost, multi-accelerator systems widely exist in data centers, c…
View article: Temporal Gradient Inversion Attacks with Robust Optimization
Temporal Gradient Inversion Attacks with Robust Optimization Open
Federated Learning (FL) has emerged as a promising approach for collaborative model training without sharing private data. However, privacy concerns regarding information exchanged during FL have received significant research attention. Gr…
View article: Adaptive incentive for cross-silo federated learning: A multi-agent reinforcement learning approach
Adaptive incentive for cross-silo federated learning: A multi-agent reinforcement learning approach Open
Cross-silo federated learning (FL) is a typical FL that enables organizations(e.g., financial or medical entities) to train global models on isolated data. Reasonable incentive is key to encouraging organizations to contribute data. Howeve…
View article: On Collective Robustness of Bagging Against Data Poisoning
On Collective Robustness of Bagging Against Data Poisoning Open
Bootstrap aggregating (bagging) is an effective ensemble protocol, which is believed can enhance robustness by its majority voting mechanism. Recent works further prove the sample-wise robustness certificates for certain forms of bagging (…
View article: On Understanding and Mitigating the Dimensional Collapse of Graph Contrastive Learning: a Non-Maximum Removal Approach
On Understanding and Mitigating the Dimensional Collapse of Graph Contrastive Learning: a Non-Maximum Removal Approach Open
Graph Contrastive Learning (GCL) has shown promising performance in graph representation learning (GRL) without the supervision of manual annotations. GCL can generate graph-level embeddings by maximizing the Mutual Information (MI) betwee…
View article: Toward the prevention of coronavirus infection: what role can polymers play?
Toward the prevention of coronavirus infection: what role can polymers play? Open
Severe acute respiratory syndrome-associated coronavirus 2 has caused a global public health crisis with high rates of infection and mortality. Treatment and prevention approaches include vaccine development, the design of small-molecule a…
View article: Association: Remind Your GAN not to Forget
Association: Remind Your GAN not to Forget Open
Neural networks are susceptible to catastrophic forgetting. They fail to preserve previously acquired knowledge when adapting to new tasks. Inspired by human associative memory system, we propose a brain-like approach that imitates the ass…
View article: Distorted image restoration using stacked adversarial network
Distorted image restoration using stacked adversarial network Open
Liquify is a common technique for distortion. Due to the uncertainty in the distortion variation, restoring distorted images caused by liquify filter is a challenging task. Unlike existing methods mainly designed for specific single deform…
View article: Generative and Discriminative Learning for Distorted Image Restoration
Generative and Discriminative Learning for Distorted Image Restoration Open
Liquify is a common technique for image editing, which can be used for image distortion. Due to the uncertainty in the distortion variation, restoring distorted images caused by liquify filter is a challenging task. To edit images in an ef…
View article: A Framework of Randomized Selection Based Certified Defenses Against Data Poisoning Attacks
A Framework of Randomized Selection Based Certified Defenses Against Data Poisoning Attacks Open
Neural network classifiers are vulnerable to data poisoning attacks, as attackers can degrade or even manipulate their predictions thorough poisoning only a few training samples. However, the robustness of heuristic defenses is hard to mea…
View article: Dapper: An Adaptive Manager for Large-Capacity Persistent Memory
Dapper: An Adaptive Manager for Large-Capacity Persistent Memory Open
Smart applications are becoming more data centric, and the need for businesses to quickly manage vast amounts of data continues to challenge today’s computing infrastructure. Nevertheless, main memory systems consisting entirely of dynamic…
View article: Green Video Streaming in LTE Networks: A Client-Side Method for Power Efficiency of Mobile Devices
Green Video Streaming in LTE Networks: A Client-Side Method for Power Efficiency of Mobile Devices Open
Nowadays mobile data traffic is soaring gradually year by year, the total monthly mobile data traffic (includes uplink and downlink) has come to more than 3,500 Petabytes and the growing trend is continuing.Video streaming demand is the si…