Search Results for author:
Found 112 papers, 24 papers with code
Prediction-Guided Multi-Objective Reinforcement Learning for Continuous Robot Control
Many real-world control problems involve conflicting objectives where we desire a dense and high-quality set of control policies that are optimal for different objective preferences (called Pareto-optimal).
Multi-Objective Reinforcement Learning
reinforcement-learning
LMEraser: Large Model Unlearning through Adaptive Prompt Tuning
To address the growing demand for privacy protection in machine learning, we propose a novel and efficient machine unlearning approach for \textbf{L}arge \textbf{M}odels, called \textbf{LM}Eraser.
AdaDemo: Data-Efficient Demonstration Expansion for Generalist Robotic Agent
Encouraged by the remarkable achievements of language and vision foundation models, developing generalist robotic agents through imitation learning, using large demonstration datasets, has become a prominent area of interest in robot learning.
Rethinking Resource Management in Edge Learning: A Joint Pre-training and Fine-tuning Design Paradigm
Based on our analytical results, we then propose a joint communication and computation resource management design to minimize an average squared gradient norm bound, subject to constraints on the transmit power, overall system energy consumption, and training delay.
Taming Cross-Domain Representation Variance in Federated Prototype Learning with Heterogeneous Data Domains
Federated learning (FL) allows collaborative machine learning training without sharing private data.
FedMM: Federated Multi-Modal Learning with Modality Heterogeneity in Computational Pathology
The fusion of complementary multimodal information is crucial in computational pathology for accurate diagnostics.
MV2MAE: Multi-View Video Masked Autoencoders
We report state-of-the-art results on the NTU-60, NTU-120 and ETRI datasets, as well as in the transfer learning setting on NUCLA, PKU-MMD-II and ROCOG-v2 datasets, demonstrating the robustness of our approach.
Evaluating and Enhancing Large Language Models Performance in Domain-specific Medicine: Osteoarthritis Management with DocOA
This study focused on evaluating and enhancing the clinical capabilities of LLMs in specific domains, using osteoarthritis (OA) management as a case study.
Integrated Sensing, Communication, and Powering (ISCAP): Towards Multi-functional 6G Wireless Networks
Specifically, a multi-functional base station (BS) can enable multi-functional transmission, by exploiting the same radio signals to perform target/environment sensing, wireless communication, and wireless power transfer (WPT), simultaneously.
Online Vertical Federated Learning for Cooperative Spectrum Sensing
However, deep learning-based CSS methods often rely on centralized learning, posing challenges like communication overhead and data privacy risks.
Federated Learning with Instance-Dependent Noisy Label
We introduce a novel algorithm called FedBeat (Federated Learning with Bayesian Ensemble-Assisted Transition Matrix Estimation).
IL-NeRF: Incremental Learning for Neural Radiance Fields with Camera Pose Alignment
This poses a paradox as the necessary camera pose must be estimated from the entire dataset, even though the data arrives sequentially and future chunks are inaccessible.
Signatures Meet Dynamic Programming: Generalizing Bellman Equations for Trajectory Following
As a specific case of our framework, we devise a model predictive control method for path tracking.
Knowledge Base Enabled Semantic Communication: A Generative Perspective
Semantic communication is widely touted as a key technology for propelling the sixth-generation (6G) wireless networks.
Fully-Passive versus Semi-Passive IRS-Enabled Sensing: SNR and CRB Comparison
Accordingly, we analyze the sensing signal-to-noise ratio (SNR) performance for a target detection scenario and the estimation Cram\'er-Rao bound (CRB) performance for a target's direction-of-arrival (DoA) estimation scenario, in cases where the transmit beamforming at the BS and the reflective beamforming at the IRS are jointly optimized.
CAFE: Carbon-Aware Federated Learning in Geographically Distributed Data Centers
Training large-scale artificial intelligence (AI) models demands significant computational power and energy, leading to increased carbon footprint with potential environmental repercussions.
Vision-Language Foundation Models as Effective Robot Imitators
We believe RoboFlamingo has the potential to be a cost-effective and easy-to-use solution for robotics manipulation, empowering everyone with the ability to fine-tune their own robotics policy.
An Overview on IEEE 802.11bf: WLAN Sensing
To resolve this issue, a new Task Group (TG), namely IEEE 802. 11bf, has been established by the IEEE 802. 11 working group, with the objective of creating a new amendment to the WLAN standard to meet advanced sensing requirements while minimizing the effect on communications.
InViG: Benchmarking Interactive Visual Grounding with 500K Human-Robot Interactions
Ambiguity is ubiquitous in human communication.
Federated Deep Multi-View Clustering with Global Self-Supervision
Second, the storage and usage of data from multiple clients in a distributed environment can lead to incompleteness of multi-view data.
Sensing With Random Signals
Radar systems typically employ well-designed deterministic signals for target sensing.
OFVL-MS: Once for Visual Localization across Multiple Indoor Scenes
In this work, we seek to predict camera poses across scenes with a multi-task learning manner, where we view the localization of each scene as a new task.
LLM-Mini-CEX: Automatic Evaluation of Large Language Model for Diagnostic Conversation
Despite their alluring technological potential, there is no unified and comprehensive evaluation criterion, leading to the inability to evaluate the quality and potential risks of medical LLMs, further hindering the application of LLMs in medical treatment scenarios.
Machine Unlearning: Solutions and Challenges
Machine learning models may inadvertently memorize sensitive, unauthorized, or malicious data, posing risks of privacy breaches, security vulnerabilities, and performance degradation.
Fully-Passive versus Semi-Passive IRS-Enabled Sensing: SNR Analysis
This paper compares the signal-to-noise ratio (SNR) performance between the fully-passive intelligent reflecting surface (IRS)-enabled non-line-of-sight (NLoS) sensing versus its semi-passive counterpart.
TableGPT: Towards Unifying Tables, Nature Language and Commands into One GPT
Tables are prevalent in real-world databases, requiring significant time and effort for humans to analyze and manipulate.
Over-the-Air Computation in OFDM Systems with Imperfect Channel State Information
In particular, we consider two scenarios with best-effort and error-constrained computation tasks, with the objectives of minimizing the average computation mean squared error (MSE) and the computation outage probability over the multiple subcarriers, respectively.
Cramér-Rao Bound Minimization for IRS-Enabled Multiuser Integrated Sensing and Communications
Accordingly, we model two types of CU receivers, namely Type-I and Type-II CU receivers, which do not have and have the capability of canceling the interference from the sensing signals, respectively.
RVT: Robotic View Transformer for 3D Object Manipulation
In simulations, we find that a single RVT model works well across 18 RLBench tasks with 249 task variations, achieving 26% higher relative success than the existing state-of-the-art method (PerAct).
Ranked #3 on
Robot Manipulation
on RLBench
ContrastNet: A Contrastive Learning Framework for Few-Shot Text Classification
Few-shot text classification has recently been promoted by the meta-learning paradigm which aims to identify target classes with knowledge transferred from source classes with sets of small tasks named episodes.
MedGPTEval: A Dataset and Benchmark to Evaluate Responses of Large Language Models in Medicine
The responses generated by chatbots based on LLMs are recorded for blind evaluations by five licensed medical experts.
Towards clinical AI fairness: A translational perspective
In this paper, we discuss the misalignment between technical and clinical perspectives of AI fairness, highlight the barriers to AI fairness' translation to healthcare, advocate multidisciplinary collaboration to bridge the knowledge gap, and provide possible solutions to address the clinical concerns pertaining to AI fairness.
Joint Client Assignment and UAV Route Planning for Indirect-Communication Federated Learning
The use of indirect communication presents new challenges for convergence analysis and optimization, as the delay introduced by the transporters' movement creates issues for both global model dissemination and local model collection.
Accelerating Hybrid Federated Learning Convergence under Partial Participation
In this paper, we provide theoretical analysis of hybrid FL under clients' partial participation to validate that partial participation is the key constraint on convergence speed.
Investigating and Mitigating the Side Effects of Noisy Views for Self-Supervised Clustering Algorithms in Practical Multi-View Scenarios
Multi-view clustering (MVC) aims at exploring category structures among multi-view data in self-supervised manners.
On the Local Cache Update Rules in Streaming Federated Learning
In this study, we address the emerging field of Streaming Federated Learning (SFL) and propose local cache update rules to manage dynamic data distributions and limited cache capacity.
Generative Sentiment Transfer via Adaptive Masking
Sentiment transfer aims at revising the input text to satisfy a given sentiment polarity while retaining the original semantic content.
Federated Learning via Indirect Server-Client Communications
In this paper, we propose a novel FL framework, named FedEx (short for FL via Model Express Delivery), that utilizes mobile transporters (e. g., Unmanned Aerial Vehicles) to establish indirect communication channels between the server and the clients.
E$^3$Pose: Energy-Efficient Edge-assisted Multi-camera System for Multi-human 3D Pose Estimation
To achieve this goal, E$^3$Pose incorporates an attention-based LSTM to predict the occlusion information of each camera view and guide camera selection before cameras are selected to process the images of a scene, and runs a camera selection algorithm based on the Lyapunov optimization framework to make long-term adaptive selection decisions.
Towards High Performance One-Stage Human Pose Estimation
Making top-down human pose estimation method present both good performance and high efficiency is appealing.
Radio Frequency Fingerprints Extraction for LTE-V2X: A Channel Estimation Based Methodology
Then, we remove the impact of the wireless channel based on the channel estimate and obtain initial RFF features.
CO-Net: Learning Multiple Point Cloud Tasks at Once with A Cohesive Network
Finally, we propose a sign-based gradient surgery to promote the training of CO-Net, thereby emphasizing the usage of task-shared parameters and guaranteeing that each task can be thoroughly optimized.
Enhancing Privacy Preservation in Federated Learning via Learning Rate Perturbation
Previous attacks assume the adversary can infer the local learning rate of each client, while we observe that: (1) using the uniformly distributed random local learning rates does not incur much accuracy loss of the global model, and (2) personalizing local learning rates can mitigate the drift issue which is caused by non-IID (identically and independently distributed) data.
AD-BERT: Using Pre-trained contextualized embeddings to Predict the Progression from Mild Cognitive Impairment to Alzheimer's Disease
Materials and Methods: We identified 3657 patients diagnosed with MCI together with their progress notes from Northwestern Medicine Enterprise Data Warehouse (NMEDW) between 2000-2020.
Cramér-Rao Bound Minimization for IRS-Enabled Multiuser Integrated Sensing and Communication with Extended Target
This paper investigates an intelligent reflecting surface (IRS) enabled multiuser integrated sensing and communication (ISAC) system, which consists of one multi-antenna base station (BS), one IRS, multiple single-antenna communication users (CUs), and one extended target at the non-line-of-sight (NLoS) region of the BS.
Variational Graph Generator for Multi-View Graph Clustering
The critical point of MGC is to better utilize the view-specific and view-common information in features and graphs of multiple views.
Deep Clustering: A Comprehensive Survey
Finally, we discuss the open challenges and potential future opportunities in different fields of deep clustering.
Semi-Supervised Keypoint Detector and Descriptor for Retinal Image Matching
To attack the incompleteness of manual labeling, we propose Progressive Keypoint Expansion to enrich the keypoint labels at each training epoch.
Ranked #2 on
Image Registration
on FIRE
Intelligent Reflecting Surface Enabled Sensing: Cramér-Rao Bound Optimization
For the extended target case, we obtain the optimal transmit beamforming solution to minimize the CRB in closed form.
Task-Oriented Sensing, Computation, and Communication Integration for Multi-Device Edge AI
This paper studies a new multi-device edge artificial-intelligent (AI) system, which jointly exploits the AI model split inference and integrated sensing and communication (ISAC) to enable low-latency intelligent services at the network edge.
RoSGAS: Adaptive Social Bot Detection with Reinforced Self-Supervised GNN Architecture Search
More specifically, we consider the social bot detection problem as a user-centric subgraph embedding and classification task.
Accelerating Asynchronous Federated Learning Convergence via Opportunistic Mobile Relaying
To address this issue, the paper explores the impact of mobility on the convergence performance of asynchronous FL.
Combating Client Dropout in Federated Learning via Friend Model Substitution
Federated learning (FL) is a new distributed machine learning framework known for its benefits on data privacy and communication efficiency.
Intelligent Reflecting Surface Enabled Sensing: Cramér-Rao Lower Bound Optimization
This paper investigates intelligent reflecting surface (IRS) enabled non-line-of-sight (NLoS) wireless sensing, in which an IRS is deployed to assist an access point (AP) to sense a target in its NLoS region.
Accelerated Policy Learning with Parallel Differentiable Simulation
In this work we present a high-performance differentiable simulator and a new policy learning algorithm (SHAC) that can effectively leverage simulation gradients, even in the presence of non-smoothness.
GATE: Graph CCA for Temporal SElf-supervised Learning for Label-efficient fMRI Analysis
To improve fMRI representation learning and classification under a label-efficient setting, we propose a novel and theory-driven self-supervised learning (SSL) framework on GCNs, namely Graph CCA for Temporal self-supervised learning on fMRI analysis GATE.
On Federated Learning with Energy Harvesting Clients
Catering to the proliferation of Internet of Things devices and distributed machine learning at the edge, we propose an energy harvesting federated learning (EHFL) framework in this paper.
Evolution Gym: A Large-Scale Benchmark for Evolving Soft Robots
In this paper, we propose Evolution Gym, the first large-scale benchmark for co-optimizing the design and control of soft robots.
Vertical Federated Edge Learning with Distributed Integrated Sensing and Communication
This letter studies a vertical federated edge learning (FEEL) system for collaborative objects/human motion recognition by exploiting the distributed integrated sensing and communication (ISAC).
K-Core Decomposition on Super Large Graphs with Limited Resources
For example, the distributed K-core decomposition algorithm can scale to a large graph with 136 billion edges without losing correctness with our divide-and-conquer technique.
Automated Customization of On-Thing Inference for Quality-of-Experience Enhancement
The core of our method is a DNN selection module that learns user QoE patterns on-the-fly and identifies the best-fit DNN for on-thing inference with the learned knowledge.
Context-Aware Online Client Selection for Hierarchical Federated Learning
In addition, client selection for HFL faces more challenges than conventional FL, e. g., the time-varying connection of client-ES pairs and the limited budget of the Network Operator (NO).
Joint transmit and reflective beamforming for IRS-assisted integrated sensing and communication
This paper studies an intelligent reflecting surface (IRS)-assisted integrated sensing and communication (ISAC) system, in which one IRS is deployed to not only assist the wireless communication from a multi-antenna base station (BS) to a single-antenna communication user (CU), but also create virtual line-of-sight (LoS) links for sensing targets at areas with LoS links blocked.
A System for General In-Hand Object Re-Orientation
The videos of the learned policies are available at: https://taochenshh. github. io/projects/in-hand-reorientation.
FedSEAL: Semi-Supervised Federated Learning with Self-Ensemble Learning and Negative Learning
Federated learning (FL), a popular decentralized and privacy-preserving machine learning (FL) framework, has received extensive research attention in recent years.
Closed-Loop Control of Additive Manufacturing via Reinforcement Learning
We further show that in combination with reinforcement learning, our model can be used to discover control policies that outperform state-of-the-art controllers.
Integrated Sensing and Communications: Towards Dual-functional Wireless Networks for 6G and Beyond
As the standardization of 5G is being solidified, researchers are speculating what 6G will be.
An End-to-End Differentiable Framework for Contact-Aware Robot Design
Existing methods for co-optimization are limited and fail to explore a rich space of designs.
Probabilistic Human Motion Prediction via A Bayesian Neural Network
The experimental results show that our approach makes the interaction more efficient and safer.
Multi-level Feature Learning for Contrastive Multi-view Clustering
Our method learns different levels of features from the raw features, including low-level features, high-level features, and semantic labels/features in a fusion-free manner, so that it can effectively achieve the reconstruction objective and the consistency objectives in different feature spaces.
Multi-VAE: Learning Disentangled View-common and View-peculiar Visual Representations for Multi-view Clustering
The prior of view-common variable obeys approximately discrete Gumbel Softmax distribution, which is introduced to extract the common cluster factor of multiple views.
Cross-hospital Sepsis Early Detection via Semi-supervised Optimal Transport with Self-paced Ensemble
To address this issue, we propose a novel semi-supervised transfer learning framework based on optimal transport theory and self-paced ensemble for Sepsis early detection, called SPSSOT, which can efficiently transfer knowledge from the source hospital (with rich labeled data) to the target hospital (with scarce labeled data).
DiffCloth: Differentiable Cloth Simulation with Dry Frictional Contact
This work presents a differentiable cloth simulator whose additional gradient information facilitates cloth-related applications.
Transparent Model of Unabridged Data (TMUD)
Recent advancements in computational power and algorithms have enabled unabridged data (e. g., raw images or audio) to be used as input in some models (e. g., deep learning).
Resource Rationing for Wireless Federated Learning: Concept, Benefits, and Challenges
We advocate a new resource allocation framework, which we term resource rationing, for wireless federated learning (FL).
Self-supervised Discriminative Feature Learning for Deep Multi-view Clustering
To leverage the multi-view complementary information, we concatenate all views' embedded features to form the global features, which can overcome the negative impact of some views' unclear clustering structures.
Autodidactic Neurosurgeon: Collaborative Deep Inference for Mobile Edge Intelligence via Online Learning
The basic idea of this system is to partition a deep neural network (DNN) into a front-end part running on the mobile device and a back-end part running on the edge server, with the key challenge being how to locate the optimal partition point to minimize the end-to-end inference delay.
Personalized Education in the AI Era: What to Expect Next?
The objective of personalized learning is to design an effective knowledge acquisition track that matches the learner's strengths and bypasses her weaknesses to ultimately meet her desired goal.
Bandwidth Allocation for Multiple Federated Learning Services in Wireless Edge Networks
For cooperative FL service providers, we design a distributed bandwidth allocation algorithm to optimize the overall performance of multiple FL services, meanwhile cater to the fairness among FL services and the privacy of clients.
Passenger Mobility Prediction via Representation Learning for Dynamic Directed and Weighted Graph
Consequently, the spatiotemporal passenger demand records naturally carry dynamic patterns in the constructed graphs, where the edges also encode important information about the directions and volume (i. e., weights) of passenger demands between two connected regions.
A Deep Reinforcement Learning Based Multi-Criteria Decision Support System for Textile Manufacturing Process Optimization
Textile manufacturing is a typical traditional industry involving high complexity in interconnected processes with limited capacity on the application of modern technologies.
Multi-Objective Optimization of the Textile Manufacturing Process Using Deep-Q-Network Based Multi-Agent Reinforcement Learning
The case study result reflects that the proposed MARL system is possible to achieve the optimal solutions for the textile ozonation process and it performs better than the traditional approaches.
A Comprehensive Overview on 5G-and-Beyond Networks with UAVs: From Communications to Sensing and Intelligence
On the other hand, providing such communication services simultaneously for both UAV and ground users poses new challenges due to the need for ubiquitous 3D signal coverage as well as the strong air-ground network interference.
Neural Dialogue State Tracking with Temporally Expressive Networks
Existing DST models either ignore temporal feature dependencies across dialogue turns or fail to explicitly model temporal state dependencies in a dialogue.
Parallel Interactive Networks for Multi-Domain Dialogue State Generation
In this study, we argue that the incorporation of these dependencies is crucial for the design of MDST and propose Parallel Interactive Networks (PIN) to model these dependencies.
Dialogue State Tracking
Multi-domain Dialogue State Tracking
A(DP)$^2$SGD: Asynchronous Decentralized Parallel Stochastic Gradient Descent with Differential Privacy
A popular distributed learning strategy is federated learning, where there is a central server storing the global model and a set of local computing nodes updating the model parameters with their corresponding data.
Deep Embedded Multi-view Clustering with Collaborative Training
Firstly, the embedded representations of multiple views are learned individually by deep autoencoders.
Adversarial Machine Learning based Partial-model Attack in IoT
In this paper, we propose an adversarial machine learning based partial-model attack in the data fusion/aggregation process of IoT by only controlling a small part of the sensing devices.
Hybrid Beamforming for Massive MIMO Over-the-Air Computation
It is shown that for the special case with a fully-digital receiver at the AP, the achieved MSE of the massive MIMO AirComp system is inversely proportional to the number of receive antennas.
Time-Division Energy Beamforming for Multiuser Wireless Power Transfer with Non-Linear Energy Harvesting
Energy beamforming has emerged as a promising technique for enhancing the energy transfer efficiency of wireless power transfer (WPT).
Client Selection and Bandwidth Allocation in Wireless Federated Learning Networks: A Long-Term Perspective
This paper studies federated learning (FL) in a classic wireless network, where learning clients share a common wireless link to a coordinating server to perform federated model training using their local data.
Energy-Efficient Federated Edge Learning with Joint Communication and Computation Design
Under both protocols, we minimize the total energy consumption at all edge devices over a particular finite training duration subject to a given training accuracy, by jointly optimizing the transmission power and rates at edge devices for uploading MLparameters and their central processing unit frequencies for local update.
Information Theory Signal Processing Information Theory
Max-Min Fairness in IRS-Aided Multi-Cell MISO Systems with Joint Transmit and Reflective Beamforming
This paper investigates an intelligent reflecting surface (IRS)-aided multi-cell multiple-input single-output (MISO) system with several multi-antenna base stations (BSs) each communicating with a single-antenna user, in which an IRS is dedicatedly deployed for assisting the wireless transmission and suppressing the inter-cell interference.
D2D-Enabled Data Sharing for Distributed Machine Learning at Wireless Network Edge
Mobile edge learning is an emerging technique that enables distributed edge devices to collaborate in training shared machine learning models by exploiting their local data samples and communication and computation resources.
Federated Learning for Healthcare Informatics
With the rapid development of computer software and hardware technologies, more and more healthcare data are becoming readily available from clinical institutions, patients, insurance companies and pharmaceutical industries, among others.
D3PG: Deep Differentiable Deterministic Policy Gradients
Over the last decade, two competing control strategies have emerged for solving complex control tasks with high efficacy.
The Tradeoff Between Privacy and Accuracy in Anomaly Detection Using Federated XGBoost
Our proposed federated XGBoost algorithm incorporates data aggregation and sparse federated update processes to balance the tradeoff between privacy and learning performance.
When Attackers Meet AI: Learning-empowered Attacks in Cooperative Spectrum Sensing
In this paper, we revisit this security vulnerability as an adversarial machine learning problem and propose a novel learning-empowered attack framework named Learning-Evaluation-Beating (LEB) to mislead the fusion center.
Bilevel Distance Metric Learning for Robust Image Recognition
Metric learning, aiming to learn a discriminative Mahalanobis distance matrix M that can effectively reflect the similarity between data samples, has been widely studied in various image recognition problems.
Contextual Combinatorial Multi-armed Bandits with Volatile Arms and Submodular Reward
In this paper, we study the stochastic contextual combinatorial multi-armed bandit (CC-MAB) framework that is tailored for volatile arms and submodular reward functions.
Spatio-temporal Edge Service Placement: A Bandit Learning Approach
To solve this problem and optimize the edge computing performance, we propose SEEN, a Spatial-temporal Edge sErvice placemeNt algorithm.
DeepN-JPEG: A Deep Neural Network Favorable JPEG-based Image Compression Framework
To reduce the data storage and transfer overhead in smart resource-limited Internet-of-Thing (IoT) systems, effective data compression is a "must-have" feature before transferring real-time produced dataset for training or classification.
Online Learning for Offloading and Autoscaling in Energy Harvesting Mobile Edge Computing
Mobile edge computing (a. k. a.
A Contextual Bandit Approach for Stream-Based Active Learning
The key feature of our algorithm is that in addition to sending a query to an annotator for the ground truth, prior information about the ground truth learned by the learner is sent together, thereby reducing the query cost.
Efficient Estimation in the Tails of Gaussian Copulas
The first of our proposed estimators $\estOpt$ is the "full-information" estimator that actively exploits such local structure to achieve bounded relative error in Gaussian settings.
Personalized Course Sequence Recommendations
Given the variability in student learning it is becoming increasingly important to tailor courses as well as course sequences to student needs.
A new humanlike facial attractiveness predictor with cascaded fine-tuning deep learning model
This paper proposes a deep leaning method to address the challenging facial attractiveness prediction problem.
SCUT-FBP: A Benchmark Dataset for Facial Beauty Perception
In this paper, a novel face dataset with attractiveness ratings, namely, the SCUT-FBP dataset, is developed for automatic facial beauty perception.
Predicting Grades
We derive a confidence estimate for the prediction accuracy and demonstrate the performance of our algorithm on a dataset obtained based on the performance of approximately 700 UCLA undergraduate students who have taken an introductory digital signal processing over the past 7 years.
Forecasting Popularity of Videos using Social Media
This paper presents a systematic online prediction method (Social-Forecast) that is capable to accurately forecast the popularity of videos promoted by social media.
