347 citations · 684 across the 26 of their papers we have counts for
16 papers · 1 filter
FAST: Federated Active Learning with Foundation Models for Communication-efficient Sampling and Training
Haoyuan Li, Mathias Funk, Jindong Wang +1
Federated Active Learning (FAL) has emerged as a promising framework to leverage large quantities of unlabeled data across distributed clients while preserving data privacy. Howeve…
PedSleepMAE: Generative Model for Multimodal Pediatric Sleep Signals
Saurav R. Pandey, Aaqib Saeed, Harlin Lee
Pediatric sleep is an important but often overlooked area in health informatics. We present PedSleepMAE, a generative model that fully leverages multimodal pediatric sleep signals…
Collaboratively Learning Federated Models from Noisy Decentralized Data
Haoyuan Li, Mathias Funk, Nezihe Merve Gürel +1
Federated learning (FL) has emerged as a prominent method for collaboratively training machine learning models using local data from edge devices, all while keeping data decentrali…
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…
Federated Fine-Tuning of Foundation Models via Probabilistic Masking
Vasileios Tsouvalas, Yuki Asano, Aaqib Saeed
Foundation Models (FMs) have revolutionized machine learning with their adaptability and high performance across tasks; yet, their integration into Federated Learning (FL) is chall…
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…
Binary Early-Exit Network for Adaptive Inference on Low-Resource Devices
Aaqib Saeed
Deep neural networks have significantly improved performance on a range of tasks with the increasing demand for computational resources, leaving deployment on low-resource devices…
Beyond Just Vision: A Review on Self-Supervised Representation Learning on Multimodal and Temporal Data
Shohreh Deldari, Hao Xue, Aaqib Saeed +3
Recently, Self-Supervised Representation Learning (SSRL) has attracted much attention in the field of computer vision, speech, natural language processing (NLP), and recently, with…
Consistency Training of Multi-exit Architectures for Sensor Data
Aaqib Saeed
Deep neural networks have become larger over the years with increasing demand of computational resources for inference; incurring exacerbate costs and leaving little room for deplo…
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…
ProcessTransformer: Predictive Business Process Monitoring with Transformer Network
Zaharah A. Bukhsh, Aaqib Saeed, Remco M. Dijkman
Predictive business process monitoring focuses on predicting future characteristics of a running process using event logs. The foresight into process execution promises great poten…
Sense and Learn: Self-Supervision for Omnipresent Sensors
Aaqib Saeed, Victor Ungureanu, Beat Gfeller
Learning general-purpose representations from multisensor data produced by the omnipresent sensing systems (or IoT in general) has numerous applications in diverse use cases. Exist…
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…
Personalized Driver Stress Detection with Multi-task Neural Networks using Physiological Signals
Aaqib Saeed, Stojan Trajanovski
Stress can be seen as a physiological response to everyday emotional, mental and physical challenges. A long-term exposure to stressful situations can have negative health conseque…