Policy-Induced Unsupervised Feature Selection: A Networking Case Study

Taghia, Jalil; Moradi, Farnaz; Larsson, Hannes; Lan, Xiaoyu; Ebrahimi, Masoumeh; Johnsson, Andreas

doi:10.1109/infocom48880.2022.9796928

Cited by 4 publications

(3 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are 197 features for agents of KV service, and 182 features for agents of VoD service. The data splits used in this work are available through [7].…”

Section: Emulation Of Multiple Datasets For Fl Agentsmentioning

confidence: 99%

“…The main contributions of this paper are as follows: (i) we introduce the scenario of service performance prediction in multi-operator network environments and provide an evaluation based on traces from a realistic testbed 1 ; (ii) we study the heterogeneity of the data and discuss how it can affect model performance; (iii) we compare different learning strategies and provide guidelines to balance model performance and privacy; (iv) we provide initial results on challenges in optimizing FL models for a ixed and limited budget on the communication rounds. 1 The FL-prepared traces are available through [7].…”

mentioning

confidence: 99%

See 1 more Smart Citation

Federated learning for performance prediction in multi-operator environments

Lan¹,

Taghia²,

Moradi³

et al. 2023

ITU J-FET

View full text Add to dashboard Cite

Telecom vendors and operators deliver services with strict requirements on performance, over complex and sometimes partly shared network infrastructures. A key enabler for network and service management in such environments is knowledge sharing, and the use of data-driven models for performance prediction, forecasting, and troubleshooting. In this paper, we outline a multi-operator service metrics prediction framework using federated learning that allows privacy-preserved knowledge-sharing across operators for improved model performance, and also reduced requirements on data transfer within an operator network. Federated learning is compared against local and central learning strategies for multi-operator performance prediction, and it is shown to balance the requirements on data privacy, model performance, and the network overhead. Further, the paper provides insights on how data heterogeneity affects model performance, where the conclusion is that standard federated learning has certain robustness to data heterogeneity. Finally, we discuss the challenges related to training a federated learning model with a limited budget on the communication rounds. The evaluation is performed using a set of realistic publicly available data traces, that are adapted specifically for the purpose of studying multi-operator service performance prediction.

show abstract

“…There are 197 features for agents of KV service, and 182 features for agents of VoD service. The data splits used in this work are available through [7].…”

Section: Emulation Of Multiple Datasets For Fl Agentsmentioning

confidence: 99%

mentioning

confidence: 99%

Federated learning for performance prediction in multi-operator environments

Lan¹,

Taghia²,

Moradi³

et al. 2023

ITU J-FET

View full text Add to dashboard Cite

show abstract

“…They find that the selected feature set varies with the type of attack recorded in the dataset. In [41] the authors propose a policyinduced unsupervised feature selection method based on a concrete auto-encoder. The policies are expressed in form of must-have features, which are pre-selected for the feature set.…”

Section: Related Workmentioning

confidence: 99%