SEAMS 2024
Mon 15 - Tue 16 April 2024 Lisbon, Portugal
co-located with ICSE 2024

Addressing runtime uncertainties in Machine Learning-Enabled Systems (MLS) is crucial for maintaining Quality of Service (QoS). The Machine Learning Model Balancer is a concept that addresses these uncertainties by facilitating dynamic ML model switching, showing promise in improving QoS in MLS. Leveraging this concept, this paper introduces SWITCH, an exemplar developed to enhance self-adaptive capabilities in such systems through dynamic model switching in runtime. SWITCH is designed as a comprehensive web service catering to a broad range of ML scenarios, with its implementation demonstrated through an object detection use case. SWITCH provides researchers with a flexible platform to apply and evaluate their ML model switching strategies, aiming to enhance QoS in MLS. SWITCH features advanced input handling, real-time data processing, and logging for adaptation metrics supplemented with an interactive real-time dashboard for enhancing system observability. This paper details SWITCH’s architecture, self-adaptation strategies through ML model switching, and its empirical validation through a case study, illustrating its potential to improve QoS in MLS. By enabling a hands-on approach to explore adaptive behaviors in ML systems, SWITCH contributes a valuable tool to the SEAMS community for research into self-adaptive mechanisms for MLS and their practical applications.

Tue 16 Apr

Displayed time zone: Lisbon change

11:00 - 12:30
Session 6: Self-Recovery & Evaluation Research Track / Artifact Track at Luis de Freitas Branco
Chair(s): Dalal Alrajeh Imperial College London
Raft Protocol for Fault Tolerance and Self-Recovery in Federated LearningFULL
Research Track
Rustem Dautov SINTEF, Erik Johannes Husom SINTEF Digital
Integrating Graceful Degradation and Recovery through Requirement-driven AdaptationFULL
Research Track
Simon Chu Carnegie Mellon University, Justin Koe The Cooper Union, David Garlan Carnegie Mellon University, Eunsuk Kang Carnegie Mellon University
Learning Recovery Strategies for Dynamic Self-healing in Reactive SystemsFULL
Research Track
Mateo Sanabria Universidad de los Andes, Ivana Dusparic Trinity College Dublin, Ireland, Nicolás Cardozo Universidad de los Andes
SWITCH: An Exemplar for Evaluating Self-Adaptive ML-Enabled SystemsARTIFACT
Artifact Track
Arya Marda IIIT Hyderabad, Shubham Kulkarni IIIT Hyderabad, Karthik Vaidhyanathan IIIT Hyderabad
Pre-print Media Attached