347 citations · 483 across the 15 of their papers we have counts for
9 papers · 1 filter
Many-Task Federated Fine-Tuning via Unified Task Vectors
Vasileios Tsouvalas, Tanir Ozcelebi, Nirvana Meratnia
Federated Learning (FL) traditionally assumes homogeneous client tasks; however, in real-world scenarios, clients often specialize in diverse tasks, introducing task heterogeneity.…
Communication-Efficient Federated Learning through Adaptive Weight Clustering and Server-Side Distillation
Vasileios Tsouvalas, Aaqib Saeed, Tanir Ozcelebi +1
Federated Learning (FL) is a promising technique for the collaborative training of deep neural networks across multiple devices while preserving data privacy. Despite its potential…
FedCode: Communication-Efficient Federated Learning via Transferring Codebooks
Saeed Khalilian, Vasileios Tsouvalas, Tanir Ozcelebi +1
Federated Learning (FL) is a distributed machine learning paradigm that enables learning models from decentralized local data. While FL offers appealing properties for clients' dat…
Labeling Chaos to Learning Harmony: Federated Learning with Noisy Labels
Vasileios Tsouvalas, Aaqib Saeed, Tanir Ozcelebi +1
Federated Learning (FL) is a distributed machine learning paradigm that enables learning models from decentralized private datasets, where the labeling effort is entrusted to the c…
Privacy-preserving Speech Emotion Recognition through Semi-Supervised Federated Learning
Vasileios Tsouvalas, Tanir Ozcelebi, Nirvana Meratnia
Speech Emotion Recognition (SER) refers to the recognition of human emotions from natural speech. If done accurately, it can offer a number of benefits in building human-centered c…
Federated Self-Training for Semi-Supervised Audio Recognition
Vasileios Tsouvalas, Aaqib Saeed, Tanir Ozcelebi
Federated Learning is a distributed machine learning paradigm dealing with decentralized and personal datasets. Since data reside on devices like smartphones and virtual assistants…
Federated Self-Supervised Learning of Multi-Sensor Representations for Embedded Intelligence
Aaqib Saeed, Flora D. Salim, Tanir Ozcelebi +1
Smartphones, wearables, and Internet of Things (IoT) devices produce a wealth of data that cannot be accumulated in a centralized repository for learning supervised models due to p…
Multi-task Self-Supervised Learning for Human Activity Detection
Aaqib Saeed, Tanir Ozcelebi, Johan Lukkien
Deep learning methods are successfully used in applications pertaining to ubiquitous computing, health, and well-being. Specifically, the area of human activity recognition (HAR) i…
Learning behavioral context recognition with multi-stream temporal convolutional networks
Aaqib Saeed, Tanir Ozcelebi, Stojan Trajanovski +1
Smart devices of everyday use (such as smartphones and wearables) are increasingly integrated with sensors that provide immense amounts of information about a person's daily life s…