Difference between revisions of "Resource:Seminar"

From MobiNetS
Jump to: navigation, search
(wenliang updates seminars)
(wenliang updates seminars)
Line 21: Line 21:
}}
}}
{{Latest_seminar
{{Latest_seminar
|abstract = Recent advancements in deep neural networks (DNN) enabled various mobile deep learning applications. However, it is technically challenging to locally train a DNN model due to limited data on devices like mobile phones. Federated learning (FL) is a distributed machine learning paradigm which allows for model training on decentralized data residing on devices without breaching data privacy. Hence, FL becomes a natural choice for deploying on-device deep learning applications. However, the data residing across devices is intrinsically statistically heterogeneous (i.e., non-IID data distribution) and mobile devices usually have limited communication bandwidth to transfer local updates. Such statistical heterogeneity and communication bandwidth limit are two major bottlenecks that hinder applying FL in practice. In addition, considering mobile devices usually have limited computational resources, improving computation efficiency of training and running DNNs is critical to developing on-device deep learning applications. In this paper, we present FedMask - a communication and computation efficient FL framework. By applying FedMask, each device can learn a personalized and structured sparse DNN, which can run efficiently on devices. To achieve this, each device learns a sparse binary mask (i.e., 1 bit per network parameter) while keeping the parameters of each local model unchanged; only these binary masks will be communicated between the server and the devices. Instead of learning a shared global model in classic FL, each device obtains a personalized and structured sparse model that is composed by applying the learned binary mask to the fixed parameters of the local model. Our experiments show that compared with status quo approaches, FedMask improves the inference accuracy by 28.47% and reduces the communication cost and the computation cost by 34.48X and 2.44X. FedMask also achieves 1.56X inference speedup and reduces the energy consumption by 1.78X.
|abstract = Federated learning (FL) has emerged in edge computing to address limited bandwidth and privacy concerns of traditional cloud-based centralized training. However, the existing FL mechanisms may lead to long training time and consume a tremendous amount of communication resources. In this paper, we propose an efficient FL mechanism, which divides the edge nodes into K clusters by balanced clustering. The edge nodes in one cluster forward their local updates to cluster header for aggregation by synchronous method, called cluster aggregation, while all cluster headers perform the asynchronous method for global aggregation. This processing procedure is called hierarchical aggregation. Our analysis shows that the convergence bound depends on the number of clusters and the training epochs. We formally define the resource-efficient federated learning with hierarchical aggregation (RFL-HA) problem. We propose an efficient algorithm to determine the optimal cluster structure (i.e., the optimal value of K) with resource constraints and extend it to deal with the dynamic network conditions. Extensive simulation results obtained from our study for different models and datasets show that the proposed algorithms can reduce completion time by 34.8%-70% and the communication resource by 33.8%-56.5% while achieving a similar accuracy, compared with the well-known FL mechanisms.
|confname= Sensys 2021
|confname= INFOCOM 2021
|link=https://dl.acm.org/doi/abs/10.1145/3485730.3485929
|link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9488756
|title=FedMask: Joint Computation and Communication-Efficient Personalized Federated Learning via Heterogeneous Masking
|title=Resource-Efficient Federated Learning with Hierarchical Aggregation in Edge Computing
|speaker=Xinyu
|speaker=Jianqi
}}
{{Latest_seminar
|abstract = The increased use of deep neural networks has stimulated the growing demand for cloud-based model serving platforms. Serverless computing offers a simplified solution: users deploy models as serverless functions and let the platform handle provisioning and scaling. However, serverless functions have constrained resources in CPU and memory, making them inefficient or infeasible to serve large neural networks-which have become increasingly popular. In this paper, we present Gillis, a serverless-based model serving system that automatically partitions a large model across multiple serverless functions for faster inference and reduced memory footprint per function. Gillis employs two novel model partitioning algorithms that respectively achieve latency-optimal serving and cost-optimal serving with SLO compliance. We have implemented Gillis on three serverless platforms-AWS Lambda, Google Cloud Functions, and KNIX-with MXNet as the serving backend. Experimental evaluations against popular models show that Gillis supports serving very large neural networks, reduces the inference latency substantially, and meets various SLOs with a low serving cost.
|confname= ICDCS 2021
|link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9546452
|title=Gillis: Serving Large Neural Networks in Serverless Functions with Automatic Model Partitioning
|speaker=Kun Wang
}}
}}


Revision as of 16:30, 18 June 2022

Time: 2022-6-13 10:30
Address: 4th Research Building A527-B
Useful links: Readling list; Schedules; Previous seminars.

Latest

  1. [TMC 2022] STMARL: A Spatio-Temporal Multi-Agent Reinforcement Learning Approach for Cooperative Traffic Light Control, Xianyang
    Abstract: The development of intelligent traffic light control systems is essential for smart transportation management. While some efforts have been made to optimize the use of individual traffic lights in an isolated way, related studies have largely ignored the fact that the use of multi-intersection traffic lights is spatially influenced, as well as the temporal dependency of historical traffic status for current traffic light control. To that end, in this article, we propose a novel Spatio-Temporal Multi-Agent Reinforcement Learning (STMARL) framework for effectively capturing the spatio-temporal dependency of multiple related traffic lights and control these traffic lights in a coordinating way. Specifically, we first construct the traffic light adjacency graph based on the spatial structure among traffic lights. Then, historical traffic records will be integrated with current traffic status via Recurrent Neural Network structure. Moreover, based on the temporally-dependent traffic information, we design a Graph Neural Network based model to represent relationships among multiple traffic lights, and the decision for each traffic light will be made in a distributed way by the deep Q-learning method. Finally, the experimental results on both synthetic and real-world data have demonstrated the effectiveness of our STMARL framework, which also provides an insightful understanding of the influence mechanism among multi-intersection traffic lights.
  2. [INFOCOM 2022] Multi-Agent Distributed Reinforcement Learningfor Making Decentralized Offloading Decisions, Wenjie
    Abstract: We formulate computation offloading as a decentralized decision-making problem with autonomous agents. We design an interaction mechanism that incentivizes agents to align private and system goals by balancing between competition and cooperation. The mechanism provably has Nash equilibria with optimal resource allocation in the static case. For a dynamic environment, we propose a novel multi-agent online learning algorithm that learns with partial, delayed and noisy state information, and a reward signal that reduces information need to a great extent. Empirical results confirm that through learning, agents significantly improve both system and individual performance, e.g., 40% offloading failure rate reduction, 32% communication overhead reduction, up to 38% computation resource savings in low contention, 18% utilization increase with reduced load variation in high contention, and improvement in fairness. Results also confirm the algorithm's good convergence and generalization property in significantly different environments.
  3. [INFOCOM 2021] Resource-Efficient Federated Learning with Hierarchical Aggregation in Edge Computing, Jianqi
    Abstract: Federated learning (FL) has emerged in edge computing to address limited bandwidth and privacy concerns of traditional cloud-based centralized training. However, the existing FL mechanisms may lead to long training time and consume a tremendous amount of communication resources. In this paper, we propose an efficient FL mechanism, which divides the edge nodes into K clusters by balanced clustering. The edge nodes in one cluster forward their local updates to cluster header for aggregation by synchronous method, called cluster aggregation, while all cluster headers perform the asynchronous method for global aggregation. This processing procedure is called hierarchical aggregation. Our analysis shows that the convergence bound depends on the number of clusters and the training epochs. We formally define the resource-efficient federated learning with hierarchical aggregation (RFL-HA) problem. We propose an efficient algorithm to determine the optimal cluster structure (i.e., the optimal value of K) with resource constraints and extend it to deal with the dynamic network conditions. Extensive simulation results obtained from our study for different models and datasets show that the proposed algorithms can reduce completion time by 34.8%-70% and the communication resource by 33.8%-56.5% while achieving a similar accuracy, compared with the well-known FL mechanisms.
  4. [ICDCS 2021] Gillis: Serving Large Neural Networks in Serverless Functions with Automatic Model Partitioning, Kun Wang
    Abstract: The increased use of deep neural networks has stimulated the growing demand for cloud-based model serving platforms. Serverless computing offers a simplified solution: users deploy models as serverless functions and let the platform handle provisioning and scaling. However, serverless functions have constrained resources in CPU and memory, making them inefficient or infeasible to serve large neural networks-which have become increasingly popular. In this paper, we present Gillis, a serverless-based model serving system that automatically partitions a large model across multiple serverless functions for faster inference and reduced memory footprint per function. Gillis employs two novel model partitioning algorithms that respectively achieve latency-optimal serving and cost-optimal serving with SLO compliance. We have implemented Gillis on three serverless platforms-AWS Lambda, Google Cloud Functions, and KNIX-with MXNet as the serving backend. Experimental evaluations against popular models show that Gillis supports serving very large neural networks, reduces the inference latency substantially, and meets various SLOs with a low serving cost.


History

History

2024

2023

2022

2021

2020

  • [Topic] [ The path planning algorithm for multiple mobile edge servers in EdgeGO], Rong Cong, 2020-11-18

2019

2018

2017

Instructions

请使用Latest_seminar和Hist_seminar模板更新本页信息.

    • 修改时间和地点信息
    • 将当前latest seminar部分的code复制到这个页面中
    • 将{{Latest_seminar... 修改为 {{Hist_seminar...，并增加对应的日期信息|date=
    • 填入latest seminar各字段信息
    • link请务必不要留空，如果没有link则填本页地址 https://mobinets.org/index.php?title=Resource:Seminar
  • 格式说明
    • Latest_seminar:

{{Latest_seminar
|confname=
|link=
|title=
|speaker=
}}

    • Hist_seminar

{{Hist_seminar
|confname=
|link=
|title=
|speaker=
|date=
}}

Retrieved from "http://mobinets.cn/site/index.php?title=Resource:Seminar&oldid=2397"