Proceedings of the 3rd Workshop on Machine Learning and Systems最新文献

Towards Robust and Bias-free Federated Learning 迈向稳健和无偏见的联邦学习

Proceedings of the 3rd Workshop on Machine Learning and Systems Pub Date : 2023-05-08 DOI: 10.1145/3578356.3592576

Ousmane Touat, S. Bouchenak

引用次数: 0

Actionable Data Insights for Machine Learning 机器学习的可操作数据洞察

Proceedings of the 3rd Workshop on Machine Learning and Systems Pub Date : 2023-05-08 DOI: 10.1145/3578356.3592581

Ming-Chuan Wu, Manuel Bähr, Nils Braun, Katrin Honauer

引用次数: 0

TinyMLOps for real-time ultra-low power MCUs applied to frame-based event classification 实时超低功耗mcu的TinyMLOps应用于基于帧的事件分类

Proceedings of the 3rd Workshop on Machine Learning and Systems Pub Date : 2023-05-08 DOI: 10.1145/3578356.3592586

Minh Tri Lê, Julyan Arbel

引用次数: 1

TSMix: time series data augmentation by mixing sources TSMix:通过混合源增强时间序列数据

Proceedings of the 3rd Workshop on Machine Learning and Systems Pub Date : 2023-05-08 DOI: 10.1145/3578356.3592584

L. N. Darlow, Artjom Joosen, Martin Asenov, Qiwen Deng, Jianfeng Wang, Adam Barker

引用次数: 0

Toward Pattern-based Model Selection for Cloud Resource Forecasting 基于模式的云资源预测模型选择研究

Proceedings of the 3rd Workshop on Machine Learning and Systems Pub Date : 2023-05-08 DOI: 10.1145/3578356.3592588

Georgia Christofidi, Konstantinos Papaioannou, Thaleia Dimitra Doudali

{"title":"Toward Pattern-based Model Selection for Cloud Resource Forecasting","authors":"Georgia Christofidi, Konstantinos Papaioannou, Thaleia Dimitra Doudali","doi":"10.1145/3578356.3592588","DOIUrl":"https://doi.org/10.1145/3578356.3592588","url":null,"abstract":"Cloud resource management solutions, such as autoscaling and overcommitment policies, often leverage robust prediction models to forecast future resource utilization at the task-, job- and machine-level. Such solutions maintain a collection of different models and at decision time select to use the model that provides the best performance, typically minimizing a cost function. In this paper, we explore a more generalizable model selection approach, based on the patterns of resource usage that are common across the tasks of a job. To learn such patterns, we train a collection of Long Short Term Memory (LSTM) neural networks, at the granularity of a job. During inference, we select which model to use to predict the resource usage of a given task via distance-based time series comparisons. Our experimentation with various time series data representations and similarity metrics reveals cases where even sophisticated approaches, such as dynamic time warping, lead to suboptimal model selection and as a result significantly lower prediction accuracy. Our analysis establishes the importance and impact of pattern-based model selection, and discusses relevant challenges, opportunities and future directions based on our findings.","PeriodicalId":370204,"journal":{"name":"Proceedings of the 3rd Workshop on Machine Learning and Systems","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133092763","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Robust and Tiny Binary Neural Networks using Gradient-based Explainability Methods 基于梯度可解释性方法的鲁棒微型二值神经网络

Proceedings of the 3rd Workshop on Machine Learning and Systems Pub Date : 2023-05-08 DOI: 10.1145/3578356.3592595

Muhammad Sabih, Mikail Yayla, Frank Hannig, Jürgen Teich, Jian-Jia Chen

{"title":"Robust and Tiny Binary Neural Networks using Gradient-based Explainability Methods","authors":"Muhammad Sabih, Mikail Yayla, Frank Hannig, Jürgen Teich, Jian-Jia Chen","doi":"10.1145/3578356.3592595","DOIUrl":"https://doi.org/10.1145/3578356.3592595","url":null,"abstract":"Binary neural networks (BNNs) are a highly resource-efficient variant of neural networks. The efficiency of BNNs for tiny machine learning (TinyML) systems can be enhanced by structured pruning and making BNNs robust to faults. When used with approximate memory systems, this fault tolerance can be traded off for energy consumption, latency, or cost. For pruning, magnitude-based heuristics are not useful because the weights in a BNN can either be -1 or +1. Global pruning of BNNs has not been studied well so far. Thus, in this paper, we explore gradient-based ranking criteria for pruning BNNs and use them in combination with a sensitivity analysis. For robustness, the state-of-the-art is to train the BNNs with bit-flips in what is known as fault-aware training. We propose a method to guide fault-aware training using gradient-based explainability methods. This allows us to obtain robust and efficient BNNs for deployment on tiny devices. Experiments on audio and image processing applications show that our proposed approach outperforms the existing approaches, making it useful for obtaining efficient and robust models for a slight degradation in accuracy. This makes our approach valuable for many TinyML use cases.","PeriodicalId":370204,"journal":{"name":"Proceedings of the 3rd Workshop on Machine Learning and Systems","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132929018","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Towards A Platform and Benchmark Suite for Model Training on Dynamic Datasets 面向动态数据集模型训练的平台和基准套件

Proceedings of the 3rd Workshop on Machine Learning and Systems Pub Date : 2023-05-08 DOI: 10.1145/3578356.3592585

Maximilian Böther, F. Strati, Viktor Gsteiger, Ana Klimovic

引用次数: 1

Illuminating the hidden challenges of data-driven CDNs 阐明数据驱动cdn的隐藏挑战

Proceedings of the 3rd Workshop on Machine Learning and Systems Pub Date : 2023-05-08 DOI: 10.1145/3578356.3592574

Theophilus A. Benson

引用次数: 0

Distributed Training for Speech Recognition using Local Knowledge Aggregation and Knowledge Distillation in Heterogeneous Systems 基于局部知识聚合和知识蒸馏的异构系统语音识别分布式训练

Proceedings of the 3rd Workshop on Machine Learning and Systems Pub Date : 2023-05-08 DOI: 10.1145/3578356.3592591

Hongrui Shi, Valentin Radu, Po Yang

{"title":"Distributed Training for Speech Recognition using Local Knowledge Aggregation and Knowledge Distillation in Heterogeneous Systems","authors":"Hongrui Shi, Valentin Radu, Po Yang","doi":"10.1145/3578356.3592591","DOIUrl":"https://doi.org/10.1145/3578356.3592591","url":null,"abstract":"Data privacy and data protection are crucial issues for automatic speech recognition (ASR) system when relying on client generated data for training. The best protection is achieved when training is distributed fashion, close to the client local data, rather than centralising the training. However, distributed training suffers from system heterogeneity, due to clients having unequal computation resources, and data heterogeneity, due to training data being non-independent and identically distributed (non-IID). To tackle these challenges, we introduce FedKAD, a Federated Learning (FL) framework that uses local Knowledge Aggregation over top level feature maps and Knowledge Distillation. We show that our FedKAD achieves better communication efficiency than standard FL methods that use uniform models, due to transferring parameters of smaller size client models, and overall better accuracy than FedMD, an alternative KD-based approach designed for heterogeneous data. Our work enables faster, cheaper and more inclusive participation of clients in heterogeneous distributed training.","PeriodicalId":370204,"journal":{"name":"Proceedings of the 3rd Workshop on Machine Learning and Systems","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126715446","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Scalable High-Performance Architecture for Evolving Recommender System 不断发展的推荐系统的可扩展高性能架构

Proceedings of the 3rd Workshop on Machine Learning and Systems Pub Date : 2023-05-08 DOI: 10.1145/3578356.3592594

R. Singh, Mayank Mishra, Rekha Singhal

引用次数: 0