# EMA: Efficient Model Adaptation for Learning-based Systems

arXiv: https://arxiv.org/abs/2605.13942 · HTML: https://mlsanity.com/paper/2605.13942/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 40 references that are in the map.
- First posted on arXiv 13 May 2026.

## Builds on (most cited first, 13 of 13)

- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [Learning Scheduling Algorithms for Data Processing Clusters](https://mlsanity.com/paper/1810.01963/) (2018)
- [Active Learning on a Budget: Opposite Strategies Suit High and Low Budgets](https://mlsanity.com/paper/2202.02794/) (2022)
- [Coverage-centric Coreset Selection for High Pruning Rates](https://mlsanity.com/paper/2210.15809/) (2022)
- [NetLLM: Adapting Large Language Models for Networking](https://mlsanity.com/paper/2402.02338/) (2024)
- [FIRM: An Intelligent Fine-Grained Resource Management Framework for SLO-Oriented Microservices](https://mlsanity.com/paper/2008.08509/) (2020)
- [Teal: Learning-Accelerated Optimization of WAN Traffic Engineering](https://mlsanity.com/paper/2210.13763/) (2022)
- [Autothrottle: A Practical Bi-Level Approach to Resource Management for SLO-Targeted Microservices](https://mlsanity.com/paper/2212.12180/) (2022)
- [DART: Domain-Adversarial Residual-Transfer Networks for Unsupervised Cross-Domain Image Classification](https://mlsanity.com/paper/1812.11478/) (2018)
- [K-Medoids For K-Means Seeding](https://mlsanity.com/paper/1609.04723/) (2016)
- [Sizeless: Predicting the optimal size of serverless functions](https://mlsanity.com/paper/2010.15162/) (2020)
- [Search-based Methods for Multi-Cloud Configuration](https://mlsanity.com/paper/2204.09437/) (2022)
- [Towards Fair and Efficient Learning-based Congestion Control](https://mlsanity.com/paper/2403.01798/) (2024)

## Built on by (most cited first, 1 of 1)

- [Maintaining IoT Device Identification under Concept Drift via Budget-Aware Traffic Labeling](https://mlsanity.com/paper/2608.15465/) (2026)

## Abstract (arXiv)

Machine learning (ML) is increasingly applied to optimize system performance in tasks such as resource management and network simulation. Unlike traditional ML tasks (e.g., image classification), networked systems often operate in heterogeneous, long-running, and dynamic environment states, where input conditions (e.g., network loads) and operational objectives can shift over time and across settings. Existing learning-based systems offer little support for adaptation, resulting in costly model training, extensive data collection, degraded system performance, and slow responsiveness. This paper presents EMA, the first model adaptation system supporting learning-based systems to adapt to evolving environments with minimal operational overhead. EMA takes a system-driven, data-centric approach that accommodates diverse system and model designs while addressing two key deployment challenges. First, it reduces expensive model training by introducing state transformers that align the input state of a new environment with previously similar states, allowing models to warm-start adaptation. Second, it addresses the often-overlooked yet costly process of data labeling--collecting ground truth for exploring and training on various system decisions--by prioritizing labeling high-utility data while balancing the tradeoff between training and labeling cost. Evaluations on eight representative learning-based systems show that EMA reduces adaptation costs (e.g., GPU training time) by 14.9-42.4% while improving system performance (e.g., network throughput) by 6.9-31.3%.