6 papers
DisAgg: Distributed Aggregators for Efficient Secure Aggregation in Federated Learning
Haaris Mehmood, Giorgos Tatsis, Dimitrios Alexopoulos +4
Federated learning enables collaborative model training across distributed clients, yet vanilla FL exposes client updates to the central server. Secure-aggregation schemes protect…
Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation
Jie Xu, Haaris Mehmood, Rogier Van Dalen +2
Federated learning (FL) enables training of a global model while keeping raw data on end-devices. Despite this, FL has shown to leak private user information and thus in practice,…
Decoding Text Spans for Efficient and Accurate Named-Entity Recognition
Andrea Maracani, Savas Ozkan, Junyi Zhu +2
Named Entity Recognition (NER) is a key component in industrial information extraction pipelines, where systems must satisfy strict latency and throughput constraints in addition t…
ValSub: Subsampling Validation Data to Mitigate Forgetting during ASR Personalization
Haaris Mehmood, Karthikeyan Saravanan, Pablo Peso Parada +5
Automatic Speech Recognition (ASR) is widely used within consumer devices such as mobile phones. Recently, personalization or on-device model fine-tuning has shown that adaptation…
DP-DyLoRA: Fine-Tuning Transformer-Based Models On-Device under Differentially Private Federated Learning using Dynamic Low-Rank Adaptation
Jie Xu, Karthikeyan Saravanan, Rogier van Dalen +3
Federated learning (FL) allows clients to collaboratively train a global model without sharing their local data with a server. However, clients' contributions to the server can sti…
persoDA: Personalized Data Augmentation for Personalized ASR
Pablo Peso Parada, Spyros Fontalis, Md Asif Jalal +6
Data augmentation (DA) is ubiquitously used in training of Automatic Speech Recognition (ASR) models. DA offers increased data variability, robustness and generalization against di…