Li Ju
Doktorand vid Institutionen för informationsteknologi; Beräkningsvetenskap
- Telefon:
- 018-471 54 11
- E-post:
- li.ju@it.uu.se
- Besöksadress:
- Hus 10, Regementsvägen 10
- Postadress:
- Box 337
751 05 UPPSALA
Nyckelord
- cloud computing
- distributed systems
- federated machine learning
- distributed machine learning
Biografi
Publikationer
Urval av publikationer
Senaste publikationer
Accelerating Fair Federated Learning: Adaptive Federated Adam
Ingår i IEEE Transactions on Machine Learning in Communications and Networking, s. 1017-1032, 2024
- DOI för Accelerating Fair Federated Learning: Adaptive Federated Adam
- Ladda ner fulltext (pdf) av Accelerating Fair Federated Learning: Adaptive Federated Adam
Blades: A Unified Benchmark Suite for Byzantine Attacks and Defenses in Federated Learning
Ingår i 2024 IEEE/ACM Ninth International Conference on Internet-of-Things Design and Implementation (IoTDI), s. 158-169, 2024
Ingår i Artificial Intelligence in the Life Sciences, 2024
- DOI för Federated learning for predicting compound mechanism of action based on image-data from cell painting
- Ladda ner fulltext (pdf) av Federated learning for predicting compound mechanism of action based on image-data from cell painting
Demo Abstract: Blades: A Unified Benchmark Suite for Byzantine-Resilient in Federated Learning
Ingår i 9TH ACM/IEEE CONFERENCE ON INTERNET OF THINGS DESIGN AND IMPLEMENTATION, IOTDI 2024, s. 229-230, 2024
Proactive Autoscaling for Edge Computing Systems with Kubernetes
2021
Alla publikationer
Artiklar i tidskrift
Accelerating Fair Federated Learning: Adaptive Federated Adam
Ingår i IEEE Transactions on Machine Learning in Communications and Networking, s. 1017-1032, 2024
- DOI för Accelerating Fair Federated Learning: Adaptive Federated Adam
- Ladda ner fulltext (pdf) av Accelerating Fair Federated Learning: Adaptive Federated Adam
Ingår i Artificial Intelligence in the Life Sciences, 2024
- DOI för Federated learning for predicting compound mechanism of action based on image-data from cell painting
- Ladda ner fulltext (pdf) av Federated learning for predicting compound mechanism of action based on image-data from cell painting
Konferensbidrag
Blades: A Unified Benchmark Suite for Byzantine Attacks and Defenses in Federated Learning
Ingår i 2024 IEEE/ACM Ninth International Conference on Internet-of-Things Design and Implementation (IoTDI), s. 158-169, 2024
Demo Abstract: Blades: A Unified Benchmark Suite for Byzantine-Resilient in Federated Learning
Ingår i 9TH ACM/IEEE CONFERENCE ON INTERNET OF THINGS DESIGN AND IMPLEMENTATION, IOTDI 2024, s. 229-230, 2024
Proactive Autoscaling for Edge Computing Systems with Kubernetes
2021