Search Results for author:
Found 58 papers, 22 papers with code
Transforming Future Data Center Operations and Management via Physical AI
Our results demonstrate its superior performance over traditional time-consuming Computational Fluid Dynamics/Heat Transfer (CFD/HT) simulation, with a median absolute temperature prediction error of 0. 18 {\deg}C. This emerging approach would open doors to several potential research directions for advancing Physical AI in future DC operations.
Rethinking Key-Value Cache Compression Techniques for Large Language Model Serving
It primarily decreases the memory consumption of \texttt{KV} \texttt{cache} to reduce the computation cost.
Advancing Generative Artificial Intelligence and Large Language Models for Demand Side Management with Electric Vehicles
This paper explores the integration of LLMs into energy management, emphasizing their roles in automating the optimization of DSM strategies with electric vehicles.
ADEM-VL: Adaptive and Embedded Fusion for Efficient Vision-Language Tuning
To bridge this gap, we propose ADEM-VL, an efficient vision-language method that tunes VL models based on pretrained large language models (LLMs) by adopting a parameter-free cross-attention mechanism for similarity measurements in multimodal fusion.
Joint Input and Output Coordination for Class-Incremental Learning
This mechanism assigns different weights to different categories of data according to the gradient of the output score, and uses knowledge distillation (KD) to reduce the mutual interference between the outputs of old and new tasks.
TorchGT: A Holistic System for Large-scale Graph Transformer Training
While there emerge inspiring algorithm advancements, their practical adoption is still limited, particularly on real-world graphs involving up to millions of nodes.
Federated Learning with Only Positive Labels by Exploring Label Correlations
Specifically, FedALC estimates the label correlations in the class embedding learning for different label pairs and utilizes it to improve the model training.
Characterization of Large Language Model Development in the Datacenter
Large Language Models (LLMs) have presented impressive performance across several transformative tasks.
Confronting Reward Overoptimization for Diffusion Models: A Perspective of Inductive and Primacy Biases
Then, we surprisingly discover that dormant neurons in our critic model act as a regularization against reward overoptimization while active neurons reflect primacy bias.
PartSeg: Few-shot Part Segmentation via Part-aware Prompt Learning
In this work, we address the task of few-shot part segmentation, which aims to segment the different parts of an unseen object using very few labeled examples.
Rethinking the Localization in Weakly Supervised Object Localization
Weakly supervised object localization (WSOL) is one of the most popular and challenging tasks in computer vision.
MAS: Towards Resource-Efficient Federated Multiple-Task Learning
Then, we present our new approach, MAS (Merge and Split), to optimize the performance of training multiple simultaneous FL tasks.
Boosting Distributed Full-graph GNN Training with Asynchronous One-bit Communication
Training Graph Neural Networks (GNNs) on large graphs is challenging due to the conflict between the high memory demand and limited GPU memory.
FedABC: Targeting Fair Competition in Personalized Federated Learning
In particular, we adopt the ``one-vs-all'' training strategy in each client to alleviate the unfair competition between classes by constructing a personalized binary classification problem for each class.
Toward Efficient Language Model Pretraining and Downstream Adaptation via Self-Evolution: A Case Study on SuperGLUE
This technical report briefly describes our JDExplore d-team's Vega v2 submission on the SuperGLUE leaderboard.
Ranked #1 on
Common Sense Reasoning
on ReCoRD
Machine Learning for a Sustainable Energy Future
Transitioning from fossil fuels to renewable energy sources is a critical global challenge; it demands advances at the levels of materials, devices, and systems for the efficient harvesting, storage, conversion, and management of renewable energy.
Not All Instances Contribute Equally: Instance-adaptive Class Representation Learning for Few-Shot Visual Recognition
To address the above issues, we propose a novel metric-based meta-learning framework termed instance-adaptive class representation learning network (ICRL-Net) for few-shot visual recognition.
Smart Multi-tenant Federated Learning
In this work, we propose a smart multi-tenant FL system, MuFL, to effectively coordinate and execute simultaneous training activities.
Optimizing Performance of Federated Person Re-identification: Benchmarking and Analysis
Based on these insights, we propose three optimization approaches: (1) We adopt knowledge distillation to facilitate the convergence of FedReID by better transferring knowledge from clients to the server; (2) We introduce client clustering to improve the performance of large datasets by aggregating clients with similar data distributions; (3) We propose cosine distance weight to elevate performance by dynamically updating the weights for aggregation depending on how well models are trained in clients.
Deep Learning Workload Scheduling in GPU Datacenters: Taxonomy, Challenges and Vision
Deep learning (DL) shows its prosperity in a wide variety of fields.
Federated Unsupervised Domain Adaptation for Face Recognition
To address this problem, we propose federated unsupervised domain adaptation for face recognition, FedFR.
Divergence-aware Federated Self-Supervised Learning
Using the framework, our study uncovers unique insights of FedSSL: 1) stop-gradient operation, previously reported to be essential, is not always necessary in FedSSL; 2) retaining local knowledge of clients in FedSSL is particularly beneficial for non-IID data.
Characterization and Prediction of Deep Learning Workloads in Large-Scale GPU Datacenters
Modern GPU datacenters are critical for delivering Deep Learning (DL) models and services in both the research community and industry.
Collaborative Unsupervised Visual Representation Learning from Decentralized Data
In this framework, each party trains models from unlabeled data independently using contrastive learning with an online network and a target network.
Joint Optimization in Edge-Cloud Continuum for Federated Unsupervised Person Re-identification
We present FedUReID, a federated unsupervised person ReID system to learn person ReID models without any labels while preserving privacy.
Are Missing Links Predictable? An Inferential Benchmark for Knowledge Graph Completion
We present InferWiki, a Knowledge Graph Completion (KGC) dataset that improves upon existing benchmarks in inferential ability, assumptions, and patterns.
Exploring Sequence Feature Alignment for Domain Adaptive Detection Transformers
In DQFA, a novel domain query is used to aggregate and align global context from the token sequence of both domains.
ModelCI-e: Enabling Continual Learning in Deep Learning Serving Systems
MLOps is about taking experimental ML models to production, i. e., serving the models to actual users.
ModelPS: An Interactive and Collaborative Platform for Editing Pre-trained Models at Scale
AI engineering has emerged as a crucial discipline to democratize deep neural network (DNN) models among software developers with a diverse background.
Towards Unsupervised Domain Adaptation for Deep Face Recognition under Privacy Constraints via Federated Learning
To this end, FedFR forms an end-to-end training pipeline: (1) pre-train in the source domain; (2) predict pseudo labels by clustering in the target domain; (3) conduct domain-constrained federated learning across two domains.
EasyFL: A Low-code Federated Learning Platform For Dummies
However, these platforms are complex to use and require a deep understanding of FL, which imposes high barriers to entry for beginners, limits the productivity of researchers, and compromises deployment efficiency.
A Serverless Cloud-Fog Platform for DNN-Based Video Analytics with Incremental Learning
To save bandwidth and reduce RTT, VPaaS provides a new video streaming protocol that only sends low-quality video to the cloud.
On the Practicality of Differential Privacy in Federated Learning by Tuning Iteration Times
Then, we theoretically derive: 1) the conditions for the DP based FedAvg to converge as the number of global iterations (GI) approaches infinity; 2) the method to set the number of local iterations (LI) to minimize the negative influence of DP noises.
Learning Relation Prototype from Unlabeled Texts for Long-tail Relation Extraction
In this paper, we propose a general approach to learn relation prototypesfrom unlabeled texts, to facilitate the long-tail relation extraction by transferring knowledge from the relation types with sufficient trainingdata.
Privacy-preserving Collaborative Learning with Automatic Transformation Search
Comprehensive evaluations demonstrate that the policies discovered by our method can defeat existing reconstruction attacks in collaborative learning, with high efficiency and negligible impact on the model performance.
InferBench: Understanding Deep Learning Inference Serving with an Automatic Benchmarking System
Our system design follows the best practice in DL clusters operations to expedite day-to-day DL service evaluation efforts by the developers.
Performance Optimization for Federated Person Re-identification via Benchmark Analysis
Then we propose two optimization methods: (1) To address the unbalanced weight problem, we propose a new method to dynamically change the weights according to the scale of model changes in clients in each training round; (2) To facilitate convergence, we adopt knowledge distillation to refine the server model with knowledge generated from client models on a public dataset.
MLModelCI: An Automatic Cloud Platform for Efficient MLaaS
MLModelCI provides multimedia researchers and developers with a one-stop platform for efficient machine learning (ML) services.
Hysia: Serving DNN-Based Video-to-Retail Applications in Cloud
Combining \underline{v}ideo streaming and online \underline{r}etailing (V2R) has been a growing trend recently.
Kalibre: Knowledge-based Neural Surrogate Model Calibration for Data Center Digital Twins
However, in the context of CFD, each search step requires long-lasting CFD model's iterated solving, rendering these approaches impractical with increased model complexity.
A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
Generative adversarial networks (GANs) are a hot research topic recently.
Look, Read and Feel: Benchmarking Ads Understanding with Multimodal Multitask Learning
A multitask loss function is also designed to train both the topic and sentiment prediction models jointly in an end-to-end manner.
A Survey of Predictive Maintenance: Systems, Purposes and Approaches
This paper highlights the importance of maintenance techniques in the coming industrial revolution, reviews the evolution of maintenance techniques, and presents a comprehensive literature review on the latest advancement of maintenance techniques, i. e., Predictive Maintenance (PdM), with emphasis on system architectures, optimization objectives, and optimization methods.
Soft-ranking Label Encoding for Robust Facial Age Estimation
Moreover, we also carefully analyze existing evaluation protocols for age estimation, finding that the overlap in identity between the training and testing sets affects the relative performance of different age encoding methods.
Baconian: A Unified Open-source Framework for Model-Based Reinforcement Learning
Model-Based Reinforcement Learning (MBRL) is one category of Reinforcement Learning (RL) algorithms which can improve sampling efficiency by modeling and approximating system dynamics.
Heterogeneous Multi-task Metric Learning across Multiple Domains
Heterogeneous transfer learning approaches can be adopted to remedy this drawback by deriving a metric from the learned transformation across different domains.
Transferring Knowledge Fragments for Learning Distance Metric from A Heterogeneous Domain
Some existing heterogeneous transfer learning (HTL) approaches can learn target distance metric by usually transforming the samples of source and target domain into a common subspace.
Multi-view Vector-valued Manifold Regularization for Multi-label Image Classification
In computer vision, image datasets used for classification are naturally associated with multiple labels and comprised of multiple views, because each image may contain several objects (e. g. pedestrian, bicycle and tree) and is properly characterized by multiple visual features (e. g. color, texture and shape).
Large Margin Multi-modal Multi-task Feature Extraction for Image Classification
The features used in many image analysis-based applications are frequently of very high dimension.
Cost-Sensitive Feature Selection by Optimizing F-Measures
Feature selection is beneficial for improving the performance of general machine learning tasks by extracting an informative subset from the high-dimensional features.
Optimizing Network Performance for Distributed DNN Training on GPU Clusters: ImageNet/AlexNet Training in 1.5 Minutes
To address this problem, we propose a communication backend named GradientFlow for distributed DNN training, and employ a set of network optimization techniques.
Distributed, Parallel, and Cluster Computing
Energy-Efficient Thermal Comfort Control in Smart Buildings via Deep Reinforcement Learning
We formulate the building thermal control as a cost-minimization problem which jointly considers the energy consumption of HVAC and the thermal comfort of the occupants.
Transfer Metric Learning: Algorithms, Applications and Outlooks
Distance metric learning (DML) aims to find an appropriate way to reveal the underlying data relationship.
Intelligent Trainer for Model-Based Reinforcement Learning
Model-based reinforcement learning (MBRL) has been proposed as a promising alternative solution to tackle the high sampling cost challenge in the canonical reinforcement learning (RL), by leveraging a learned model to generate synthesized data for policy training purpose.
A Survey on Consensus Mechanisms and Mining Strategy Management in Blockchain Networks
This survey is motivated by the lack of a comprehensive literature review on the development of decentralized consensus mechanisms in blockchain networks.
Cryptography and Security
Transforming Cooling Optimization for Green Data Center via Deep Reinforcement Learning
Specifically, we propose an end-to-end cooling control algorithm (CCA) that is based on the actor-critic framework and an off-policy offline version of the deep deterministic policy gradient (DDPG) algorithm.
Power Data Classification: A Hybrid of a Novel Local Time Warping and LSTM
Finally, using the power consumption data from a real data center, we show that the proposed LTW can improve the classification accuracy of DTW from about 84% to 90%.
Tensor Canonical Correlation Analysis for Multi-view Dimension Reduction
As a consequence, the high order correlation information contained in the different views is explored and thus a more reliable common subspace shared by all features can be obtained.
