Federated Anomaly Detection over Distributed Data Streams
- URL: http://arxiv.org/abs/2205.07829v2
- Date: Tue, 17 May 2022 07:23:01 GMT
- Title: Federated Anomaly Detection over Distributed Data Streams
- Authors: Paula Raissa Silva, Jo\~ao Vinagre, Jo\~ao Gama
- Abstract summary: We propose an approach to building the bridge among anomaly detection, federated learning, and data streams.
The overarching goal of the work is to detect anomalies in a federated environment over distributed data streams.
- Score: 0.0
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: Sharing of telecommunication network data, for example, even at high
aggregation levels, is nowadays highly restricted due to privacy legislation
and regulations and other important ethical concerns. It leads to scattering
data across institutions, regions, and states, inhibiting the usage of AI
methods that could otherwise take advantage of data at scale. It creates the
need to build a platform to control such data, build models or perform
calculations. In this work, we propose an approach to building the bridge among
anomaly detection, federated learning, and data streams. The overarching goal
of the work is to detect anomalies in a federated environment over distributed
data streams. This work complements the state-of-the-art by adapting the data
stream algorithms in a federated learning setting for anomaly detection and by
delivering a robust framework and demonstrating the practical feasibility in a
real-world distributed deployment scenario.
Related papers
- PeFAD: A Parameter-Efficient Federated Framework for Time Series Anomaly Detection [51.20479454379662]
We propose a.
Federated Anomaly Detection framework named PeFAD with the increasing privacy concerns.
We conduct extensive evaluations on four real datasets, where PeFAD outperforms existing state-of-the-art baselines by up to 28.74%.
arXiv Detail & Related papers (2024-06-04T13:51:08Z) - Benchmarking FedAvg and FedCurv for Image Classification Tasks [1.376408511310322]
This paper focuses on the problem of statistical heterogeneity of the data in the same federated network.
Several Federated Learning algorithms, such as FedAvg, FedProx and Federated Curvature (FedCurv) have already been proposed.
As a side product of this work, we release the non-IID version of the datasets we used so to facilitate further comparisons from the FL community.
arXiv Detail & Related papers (2023-03-31T10:13:01Z) - Clustered Data Sharing for Non-IID Federated Learning over Wireless
Networks [39.80420645943706]
Federated Learning (FL) is a distributed machine learning approach to leverage data from the Internet of Things (IoT)
Current FL algorithms face the challenges of non-independent and identically distributed (non-IID) data, which causes high communication costs and model accuracy declines.
We propose a clustered data sharing framework which spares the partial data from cluster heads to credible associates through device-to-device (D2D) communication.
arXiv Detail & Related papers (2023-02-17T07:11:02Z) - Instance Relation Graph Guided Source-Free Domain Adaptive Object
Detection [79.89082006155135]
Unsupervised Domain Adaptation (UDA) is an effective approach to tackle the issue of domain shift.
UDA methods try to align the source and target representations to improve the generalization on the target domain.
The Source-Free Adaptation Domain (SFDA) setting aims to alleviate these concerns by adapting a source-trained model for the target domain without requiring access to the source data.
arXiv Detail & Related papers (2022-03-29T17:50:43Z) - From Unsupervised to Few-shot Graph Anomaly Detection: A Multi-scale
Contrastive Learning Approach [49.439021563395976]
Anomaly detection from graph data is an important data mining task in many applications such as social networks, finance, and e-commerce.
We propose a novel framework, graph ANomaly dEtection framework with Multi-scale cONtrastive lEarning (ANEMONE in short)
By using a graph neural network as a backbone to encode the information from multiple graph scales (views), we learn better representation for nodes in a graph.
arXiv Detail & Related papers (2022-02-11T09:45:11Z) - Attentive Prototypes for Source-free Unsupervised Domain Adaptive 3D
Object Detection [85.11649974840758]
3D object detection networks tend to be biased towards the data they are trained on.
We propose a single-frame approach for source-free, unsupervised domain adaptation of lidar-based 3D object detectors.
arXiv Detail & Related papers (2021-11-30T18:42:42Z) - Local Learning Matters: Rethinking Data Heterogeneity in Federated
Learning [61.488646649045215]
Federated learning (FL) is a promising strategy for performing privacy-preserving, distributed learning with a network of clients (i.e., edge devices)
arXiv Detail & Related papers (2021-11-28T19:03:39Z) - A communication efficient distributed learning framework for smart
environments [0.4898659895355355]
This paper proposes a distributed learning framework to move data analytics closer to where data is generated.
Using distributed machine learning techniques, it is possible to drastically reduce the network overhead, while obtaining performance comparable to the cloud solution.
The analysis also shows when each distributed learning approach is preferable, based on the specific distribution of the data on the nodes.
arXiv Detail & Related papers (2021-09-27T13:44:34Z) - Learning while Respecting Privacy and Robustness to Distributional
Uncertainties and Adversarial Data [66.78671826743884]
The distributionally robust optimization framework is considered for training a parametric model.
The objective is to endow the trained model with robustness against adversarially manipulated input data.
Proposed algorithms offer robustness with little overhead.
arXiv Detail & Related papers (2020-07-07T18:25:25Z) - Scaling-up Distributed Processing of Data Streams for Machine Learning [10.581140430698103]
This paper reviews recently developed methods that focus on large-scale distributed optimization in the compute- and bandwidth-limited regime.
It focuses on methods that solve: (i) distributed convex problems, and (ii) distributed principal component analysis, which is a non problem with geometric structure that permits global convergence.
arXiv Detail & Related papers (2020-05-18T16:28:54Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.