.js-id-AI-Computing-Cyberinfrastructure
Introduction of “AI Computing Cyberinfrastructure”
The unprecedented impact of foundation model technology, represented by ChatGPT, is driving a revolutionary paradigm shift in AI, bringing new opportunities and challenges to many industries. However, the high training, inference and maintenance costs of foundation model technologies limit their widespread adoption.
Introduction of "AI Computing Cyberinfrastructure"
Introduction of “AI for Science”
AI for Science (AI4Science) is an emerging field that explores the intersection of artificial intelligence (AI) and scientific research. It leverages the power of AI techniques and algorithms to analyze vast amounts of scientific data, accelerate discovery, and enhance our understanding of complex scientific phenomena.
Introduction of "AI for Science"
Introduction of “Cloud-Edge Collaborative Large Models”
In pursuit of building open, intelligent, and efficient AI large models, we aim to address the challenges posed by diverse data and resources distributed across edge devices, which can significantly impact the performance and scalability of large models.
Introduction of "Cloud-Edge Collaborative Large Models"
Introduction of “Trustworthy AI Governance& AIGC”
The swift advancement of AI-generated content (AIGC) has empowered users to create photorealistic images and engage in meaningful dialogues with foundation models. Despite these advancements, AIGC services face challenges, including concept bleeding, hallucinations, and unsafe content generation.
Introduction of "Trustworthy AI Governance& AIGC"
(CVPR2024)DiPrompT|Disentangled Prompt Tuning for Multiple Latent Domain Generalization in Federated Learning
Federated learning (FL) has emerged as a powerful paradigm for learning from decentralized data, and federated domain generalization further considers the test dataset (target domain) is absent from the decentralized training data (source domains).
(CVPR2024)DiPrompT|Disentangled Prompt Tuning for Multiple Latent Domain Generalization in Federated Learning
(ICML2024)Amend to Alignment|Decoupled Prompt Tuning for Mitigating Spurious Correlation in Vision-Language Models
Fine-tuning the learnable prompt for a pre-trained vision-language model (VLM), such as CLIP, has demonstrated exceptional efficiency in adapting to a broad range of downstream tasks. Existing prompt tuning methods for VLMs do not distinguish spurious features introduced by biased training data from invariant features, and employ a uniform alignment process when adapting to unseen target domains.
(ICML2024)Amend to Alignment|Decoupled Prompt Tuning for Mitigating Spurious Correlation in Vision-Language Models
(VLDB2024) VeriDKG-A Verifiable SPARQL Query Engine for Decentralized Knowledge Graphs
The ability to decentralize knowledge graphs (KG) is important to exploit the full potential of the Semantic Web and realize the Web 3.0 vision. However, decentralization also renders KGs more prone to attacks with adverse effects on data integrity and query verifiability.
(VLDB2024) VeriDKG-A Verifiable SPARQL Query Engine for Decentralized Knowledge Graphs
(ICML2024) Easing Concept Bleeding in Diffusion via Entity Localization and Anchoring
When generating multi-entity scenes, stable diffusion and its derivative models frequently encounter issues of entity overlap or fusion, primarily due to cross-attention leakage. To mitigate these challenges, we propose performing differentiation and binarization on cross-attention maps to accurately locate entities within non-overlapping areas.
(ICML2024) Easing Concept Bleeding in Diffusion via Entity Localization and Anchoring
(arXiv2024) FengWu-GHR: Learning the Kilometer-scale Medium-range Global Weather Forecasting
FengWu-GHR: Learning the Kilometer-scale Medium-range Global Weather Forecasting The first data-driven global weather forecasting model running at the 0.09◦ horizontal resolution. FengWu-GHR introduces a novel approach that opens the door for operating ML-based high-resolution forecasts by inheriting prior knowledge from a pretrained low-resolution model.
(arXiv2024) FengWu-GHR: Learning the Kilometer-scale Medium-range Global Weather Forecasting
(ICML2024) Causally Motivated Personalized Federated Invariant Learning with Shortcut-Free Information-Theoretic Regularization
This paper introduces a novel method called FedPIN (Personalized Invariant Federated Learning with Shortcut-Averse Information-Theoretic Regularization) to address the out-of-distribution (OOD) generalization problem in personalized federated learning (PFL). By leveraging causal models and information-theoretic constraints, this approach aims to extract personalized invariant features while avoiding the pitfalls of spurious correlations.
(ICML2024) Causally Motivated Personalized Federated Invariant Learning with Shortcut-Free Information-Theoretic Regularization
(INFOCOM2024) Tomtit: Hierarchical Federated Fine-Tuning of Giant Models based on Autonomous Synchronization
With the rapid advancement of giant models, the paradigm of pre-training models followed by fine-tuning for specific downstream tasks has become increasingly popular. In response to the challenges faced by adapter-based fine-tuning due to insufficient data, and the scalability and inflexibility issues of existing federated fine-tuning solutions, we introduce Tomtit.
(INFOCOM2024) Tomtit: Hierarchical Federated Fine-Tuning of Giant Models based on Autonomous Synchronization
(NeurIPS2023) SwapPrompt:Test-Time Prompt Adaptation for Vision-Language Models
In this paper, we propose SwapPrompt, a novel framework that can effectively leverage the self-supervised contrastive learning to facilitate the test-time prompt adaptation. SwapPrompt employs a dual prompts paradigm, i.e., an online prompt and a target prompt that averaged from the online prompt to retain historical information.
(NeurIPS2023) SwapPrompt:Test-Time Prompt Adaptation for Vision-Language Models
(NeurIPS2023) Towards Test-Time Refusals via Concept Negation
PROTORE works by incorporating CLIP’s language-contrastive knowledge to identify the prototype of negative concepts, extract the negative features from outputs using the prototype as a prompt, and further refine the attention maps by retrieving negative features.
(NeurIPS2023) Towards Test-Time Refusals via Concept Negation
(EuroSys2024) Warming Serverless ML Inference via Inter-function Model Transformation
Serverless ML inference is an emerging cloud computing paradigm for low-cost, easy-to-manage inference services. In serverless ML inference, each call is executed in a container; however, the cold start of containers results in long inference delays.
(EuroSys2024) Warming Serverless ML Inference via Inter-function Model Transformation
(INFOCOM2024) An Elastic Transformer Serving System for Foundation Model via Token Adaptation
Transformer model empowered architectures have become a pillar of cloud services that keeps reshaping our society. However, the dynamic query loads and heterogeneous user requirements severely challenge current transformer serving systems, which rely on pre-training multiple variants of a foundation model to accommodate varying service demands.
(INFOCOM2024) An Elastic Transformer Serving System for Foundation Model via Token Adaptation
(KDD2023) Investigating Trojan Attacks on Pre-trained Language Model-powered Database Middleware
The recent success of pre-trained language models (PLMs) such as BERT has resulted in the development of various beneficial database middlewares, including natural language query interfaces and entity matching. This shift has been greatly facilitated by the extensive external knowledge of PLMs.
(KDD2023) Investigating Trojan Attacks on Pre-trained Language Model-powered Database Middleware
(IoTJ)A Unified TinyML System for Multi-modal Edge Intelligence and Real-time Visual Perception.
Our research focuses on the software and hardware synergy of on-device learning techniques, covering the scope of model-level neural network design, algorithm-level training optimization and hardware-level arithmetic acceleration.
(IoTJ)A Unified TinyML System for Multi-modal Edge Intelligence and Real-time Visual Perception.
(ATC2021) Adaptive Quantization-aware Training and Model Compression.
Our research focuses on the software and hardware synergy of on-device learning techniques, covering the scope of model-level neural network design, algorithm-level training optimization and hardware-level arithmetic acceleration.
(ATC2021) Adaptive Quantization-aware Training and Model Compression.
A Unified Contrastive Representation Learner for Cross-modal Federated Learning Systems.
Our research focuses on the software and hardware synergy of on-device learning techniques, covering the scope of model-level neural network design, algorithm-level training optimization and hardware-level arithmetic acceleration.
A Unified Contrastive Representation Learner for Cross-modal Federated Learning Systems.
(NeurIPS2022) Progressive Network Sparsification and Latent Feature Compression for Scalable Collaborative Learning.
Our research focuses on the software and hardware synergy of on-device learning techniques, covering the scope of model-level neural network design, algorithm-level training optimization and hardware-level arithmetic acceleration.
(NeurIPS2022) Progressive Network Sparsification and Latent Feature Compression for Scalable Collaborative Learning.
(AAAI2023)Masked Autoencoders for Occlusion-aware Visual Learners
Our research focuses on the software and hardware synergy of on-device learning techniques, covering the scope of model-level neural network design, algorithm-level training optimization and hardware-level arithmetic acceleration.
(AAAI2023)Masked Autoencoders for Occlusion-aware Visual Learners
Flexible Patch Skip for Real-time Visual Perception.
Our research focuses on the software and hardware synergy of on-device learning techniques, covering the scope of model-level neural network design, algorithm-level training optimization and hardware-level arithmetic acceleration.
Flexible Patch Skip for Real-time Visual Perception.
Efficient Federated Learning Framework on Heterogeneous Environment
Federated learning (FL) has been proposed as a promising solution for future AI applications with strong privacy protection. It enables distributed computing nodes to collaboratively train models without exposing their own data.
Efficient Federated Learning Framework on Heterogeneous Environment
Next generation blockchain system
Our team aims at the next-generation blockchain system with scalability, security, privacy, and intelligence and our proposed architecture is composed of 6 layers as above. In the following, the details of these 6 layers will be explained from top to bottom.
Next generation blockchain system
Radiation-free Spine Reconstruction and Posture Analysis Techniques with 3D Imaging
Scoliosis is a sideways curvature of the spine that occurs most often during thegrowth spurt just before puberty. According to the survey and statistics of China Child Development Center, more than 20% teens have scoliosis.
Radiation-free Spine Reconstruction and Posture Analysis Techniques with 3D Imaging
(TC)Heterogeneous Data & Resource Constraints- Batch Size Adaptation
To tackle non-IID data challenge in FL, we consider to design a new method to improve training efficiency of each client from the perspective of whole training process.
(TC)Heterogeneous Data \& Resource Constraints- Batch Size Adaptation
Edge AI in smart city
Research Overview Our team aims to design promising solutions for future AI applications based on edge intelligent technologies, which can empower construction, public health, environment, transportation and other industries, and promote the upgrading of urban intelligence.
Edge AI in smart city
Edge Application Layer in Blockchain-empowered Edge Learning
Blockchain-empowered edge learning is a novel distributed learning architecture to dispense with a dedicated server in traditional distributed learning and provide trustworthy training for edge devices.
Edge Application Layer in Blockchain-empowered Edge Learning
Heterogeneous Data & Expensive Communication- Layer-wised Aggregation
We design a novel pFL training framework dubbed Layer-wised Personalized Federated learning (pFedLA) that can discern the importance of each layer from different clients, and thus is able to optimize the personalized model aggregation for clients with heterogeneous data.
Heterogeneous Data \& Expensive Communication- Layer-wised Aggregation
(TKDE)Semantic Query and Index Layer in Semantic Blockchain Database
Blockchain database is a new direction that constructs index on top of blockchain to provide rich query functionalities. The existing works are either insecure because the query process separates from the blockchain consensus, or inscalable because all the data needs to be stored in the block. Therefore, we propose an authenticated semantic database layer for blockchains.
(TKDE)Semantic Query and Index Layer in Semantic Blockchain Database
Heterogeneous Hardware & Data- Parameterized Knowledge Transfer
Most existing pFL methods rely on model parameters aggregation at the server side, which require all models to have the same structure and size. Such constraints would prevent status quo pFL methods from further application in practical scenarios, where clients are often willing to own unique models, i.e., with customized neural architectures to adapt to heterogeneous capacities in computation, communication and storage space, etc. We seek to develop a novel training framework that can accommodate heterogeneous model structures for each client and achieve personalized knowledge transfer in each FL training round.
Heterogeneous Hardware \& Data- Parameterized Knowledge Transfer
(ICPP2020)Intelligent Consensus Layer in Learning-Driven Dynamic Architecture
Most existing blockchain systems adopt a static policy that cannot efciently deal with the dynamic environment in the blockchain system, i.e., joining and leaving of nodes, and malicious attack. Therefore, we propose a novel dynamic sharding-based blockchain framework to achieve a good balance between performance and security without compromising scalability under a dynamic environment.
(ICPP2020)Intelligent Consensus Layer in Learning-Driven Dynamic Architecture
Lack of participants- Incentive Mechanism Design for Federated Learning
A few of works have designed incentive mechanisms for FL, but these mechanisms only consider myopia optimization on resource consumption, which results in the lack of learning algorithm performance guarantee and long-term sustainability. We propose Chiron, an incentive-driven long-term mechanism for edge learning based on hierarchical deep reinforcement learning.
Lack of participants- Incentive Mechanism Design for Federated Learning
(INFOCOM2021)Layered Sharding Architecture for Blockchain
Most existing blockchain systems adopt a static policy that cannot efciently deal with the dynamic environment in the blockchain system, i.e., joining and leaving of nodes, and malicious attack. Therefore, we propose a novel dynamic sharding-based blockchain framework to achieve a good balance between performance and security without compromising scalability under a dynamic environment.
(INFOCOM2021)Layered Sharding Architecture for Blockchain
(DSN)Sustainable Off-chain Payment Channel Network
Payment channel network (PCN) is the most promising off-chain technologies to support massive micro payments for blockchain. The technology has been deployed in a number of blockchains including Bitcoin and Ethereum.
(DSN)Sustainable Off-chain Payment Channel Network
(TSC) Hybrid On-/Off-Chain Distributed Storage
Personal data produced from widely emerged cyberspace activities are expected to promote information dissemination and engagement, or even make business intelligence more powerful.
(TSC) Hybrid On-/Off-Chain Distributed Storage
Anti-Occlusion Human Pose Estimation for Scoliosis Rehabilitation
Physiotherapeutic scoliosis-specific exercises (PSSE) have been proved to be effective in scoliosis rehabilitation. PSSE consist of a program of curve-specific exercise protocols which are individually adapted to a patients’ curve site, magnitude, and clinical characteristics.
Anti-Occlusion Human Pose Estimation for Scoliosis Rehabilitation
Next Generation AI Video Analytics Detection System on Driving Behavior and Mental Factors
Video-based abnormal driving behavior and mental detection is becoming more and more popular. The key goal is to ensure the safety of drivers and passengers in the vehicle, and it is an essential step to realize autonomous driving at this stage.
Next Generation AI Video Analytics Detection System on Driving Behavior and Mental Factors
(INFOCOM2021)New Architectures and Methodologies for High Performance Sharding Blockchain
Blockchain draws tremendous attention from academia and industry, since it can provide distributed ledgers with data transparency, integrity, and immutability to untrusted parties for various decentralized applications.
(INFOCOM2021)New Architectures and Methodologies for High Performance Sharding Blockchain
Emergency Risk Management in Smart City
With the emergence and drastic improvement of mobile devices (e.g., phones, tablets, drones, and autonomous vehicles), we are now witnessing an exciting revolution of the digital city.
Emergency Risk Management in Smart City
Federated Learning in Resourced Constrained Mobile Edge Network
Federated learning (FL) has been proposed as a promising solution for future AI applications with strong privacy protection. It enables distributed computing nodes to collaboratively train models without exposing their own data.
Federated Learning in Resourced Constrained Mobile Edge Network