# Ekya: Continuous Learning of Video Analytics Models on Edge Compute Servers

arXiv: https://arxiv.org/abs/2012.10557 · HTML: https://mlsanity.com/paper/2012.10557/

## Key facts

- Cited by 58 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Dec 2020.

## Built on by (most cited first, 30 of 58)

- [Cost-Effective Online Multi-LLM Selection with Versatile Reward Models](https://mlsanity.com/paper/2405.16587/) (2024)
- [Federated Learning under Distributed Concept Drift](https://mlsanity.com/paper/2206.00799/) (2022)
- [GEMEL: Model Merging for Memory-Efficient, Real-Time Video Analytics at the Edge](https://mlsanity.com/paper/2201.07705/) (2022)
- [Galaxy: A Resource-Efficient Collaborative Edge AI System for In-situ Transformer Inference](https://mlsanity.com/paper/2405.17245/) (2024)
- [EdgeFM: Leveraging Foundation Model for Open-set Learning on the Edge](https://mlsanity.com/paper/2311.10986/) (2023)
- [On-device Training: A First Overview on Existing Systems](https://mlsanity.com/paper/2212.00824/) (2022)
- [Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving](https://mlsanity.com/paper/2312.05385/) (2023)
- [Asteroid: Resource-Efficient Hybrid Pipeline Parallelism for Collaborative DNN Training on Heterogeneous Edge Devices](https://mlsanity.com/paper/2408.08015/) (2024)
- [Spatial-Temporal Federated Learning for Lifelong Person Re-identification on Distributed Edges](https://mlsanity.com/paper/2207.11759/) (2022)
- [Shoggoth: Towards Efficient Edge-Cloud Collaborative Real-Time Video Inference via Adaptive Online Learning](https://mlsanity.com/paper/2306.15333/) (2023)
- [Boggart: Towards General-Purpose Acceleration of Retrospective Video Analytics](https://mlsanity.com/paper/2106.15315/) (2021)
- [Cost-effective On-device Continual Learning over Memory Hierarchy with Miro](https://mlsanity.com/paper/2308.06053/) (2023)
- [Continual Learning for Smart City: A Survey](https://mlsanity.com/paper/2404.00983/) (2024)
- [Enabling Resource-efficient AIoT System with Cross-level Optimization: A survey](https://mlsanity.com/paper/2309.15467/) (2023)
- [DaCapo: Accelerating Continuous Learning in Autonomous Systems for Video Analytics](https://mlsanity.com/paper/2403.14353/) (2024)
- [Turbo: Opportunistic Enhancement for Edge Video Analytics](https://mlsanity.com/paper/2207.00172/) (2022)
- [Edge Video Analytics: A Survey on Applications, Systems and Enabling Techniques](https://mlsanity.com/paper/2211.15751/) (2022)
- [MadEye: Boosting Live Video Analytics Accuracy with Adaptive Camera Configurations](https://mlsanity.com/paper/2304.02101/) (2023)
- [Monitoring and Adapting ML Models on Mobile Devices](https://mlsanity.com/paper/2305.07772/) (2023)
- [Delta: A Cloud-assisted Data Enrichment Framework for On-Device Continual Learning](https://mlsanity.com/paper/2410.18378/) (2024)
- [Chanakya: Learning Runtime Decisions for Adaptive Real-Time Perception](https://mlsanity.com/paper/2106.05665/) (2021)
- [Modyn: Data-Centric Machine Learning Pipeline Orchestration](https://mlsanity.com/paper/2312.06254/) (2023)
- [Compass: SLO-aware Query Planner for Compound AI Serving at Scale](https://mlsanity.com/paper/2504.16397/) (2025)
- [AVA: Towards Agentic Video Analytics with Vision Language Models](https://mlsanity.com/paper/2505.00254/) (2025)
- [View while Moving: Efficient Video Recognition in Long-untrimmed Videos](https://mlsanity.com/paper/2308.04834/) (2023)
- [AxiomVision: Accuracy-Guaranteed Adaptive Visual Model Selection for Perspective-Aware Video Analytics](https://mlsanity.com/paper/2407.20124/) (2024)
- [Moby: Empowering 2D Models for Efficient Point Cloud Analytics on the Edge](https://mlsanity.com/paper/2302.09221/) (2023)
- [A Scene-aware Models Adaptation Scheme for Cross-scene Online Inference on Mobile Devices](https://mlsanity.com/paper/2407.03331/) (2024)
- [Federated Learning Clients Clustering with Adaptation to Data Drifts](https://mlsanity.com/paper/2411.01580/) (2024)
- [LeMix: Unified Scheduling for LLM Training and Inference on Multi-GPU Systems](https://mlsanity.com/paper/2507.21276/) (2025)

## Abstract (arXiv)

Video analytics applications use edge compute servers for the analytics of the videos (for bandwidth and privacy). Compressed models that are deployed on the edge servers for inference suffer from data drift, where the live video data diverges from the training data. Continuous learning handles data drift by periodically retraining the models on new data. Our work addresses the challenge of jointly supporting inference and retraining tasks on edge servers, which requires navigating the fundamental tradeoff between the retrained model's accuracy and the inference accuracy. Our solution Ekya balances this tradeoff across multiple models and uses a micro-profiler to identify the models that will benefit the most by retraining. Ekya's accuracy gain compared to a baseline scheduler is 29% higher, and the baseline requires 4x more GPU resources to achieve the same accuracy as Ekya.