48 citations · 179 across the 37 of their papers we have counts for
21 papers · 1 filter
AdaNODEs: Test Time Adaptation for Time Series Forecasting Using Neural ODEs
Ting Dang, Soumyajit Chatterjee, Hong Jia +3
Test time adaptation (TTA) has emerged as a promising solution to adapt pre-trained models to new, unseen data distributions using unlabeled target domain data. However, most TTA m…
CLEF: Clinically-Guided Contrastive Learning for Electrocardiogram Foundation Models
Yuxuan Shu, Peter H. Charlton, Fahim Kawsar +2
The electrocardiogram (ECG) is a key diagnostic tool in cardiovascular health. Single-lead ECG recording is integrated into both clinical-grade and consumer wearables. While self-s…
Contrastive Self-Supervised Learning at the Edge: An Energy Perspective
Fernanda Famá, Roberto Pereira, Charalampos Kalalas +4
While contrastive learning (CL) shows considerable promise in self-supervised representation learning, its deployment on resource-constrained devices remains largely underexplored.…
AdaBet: Gradient-free Layer Selection for Efficient Training of Deep Neural Networks
Irene Tenison, Soumyajit Chatterjee, Fahim Kawsar +1
To utilize pre-trained neural networks on edge and mobile devices, we often require efficient adaptation to user-specific runtime data distributions while operating under limited c…
DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators
Taesik Gong, Fahim Kawsar, Chulhong Min
Tiny machine learning (TinyML) aims to run ML models on small devices and is increasingly favored for its enhanced privacy, reduced latency, and low cost. Recently, the advent of t…
PRIMUS: Pretraining IMU Encoders with Multimodal Self-Supervision
Arnav M. Das, Chi Ian Tang, Fahim Kawsar +1
Sensing human motions through Inertial Measurement Units (IMUs) embedded in personal devices has enabled significant applications in health and wellness. Labeled IMU data is scarce…
PaPaGei: Open Foundation Models for Optical Physiological Signals
Arvind Pillai, Dimitris Spathis, Fahim Kawsar +1
Photoplethysmography (PPG) is the leading non-invasive technique for monitoring biosignals and cardiovascular health, with widespread adoption in both clinical settings and consume…
Using Self-supervised Learning Can Improve Model Fairness
Sofia Yfantidou, Dimitris Spathis, Marios Constantinides +3
Self-supervised learning (SSL) has become the de facto training paradigm of large models, where pre-training is followed by supervised fine-tuning using domain-specific data and la…
Balancing Continual Learning and Fine-tuning for Human Activity Recognition
Chi Ian Tang, Lorena Qendro, Dimitris Spathis +3
Wearable-based Human Activity Recognition (HAR) is a key task in human-centric machine learning due to its fundamental understanding of human behaviours. Due to the dynamic nature…
Evaluating Fairness in Self-supervised and Supervised Models for Sequential Data
Sofia Yfantidou, Dimitris Spathis, Marios Constantinides +3
Self-supervised learning (SSL) has become the de facto training paradigm of large models where pre-training is followed by supervised fine-tuning using domain-specific data and lab…
Salted Inference: Enhancing Privacy while Maintaining Efficiency of Split Inference in Mobile Computing
Mohammad Malekzadeh, Fahim Kawsar
In split inference, a deep neural network (DNN) is partitioned to run the early part of the DNN at the edge and the later part of the DNN in the cloud. This meets two key requireme…
The first step is the hardest: Pitfalls of Representing and Tokenizing Temporal Data for Large Language Models
Dimitris Spathis, Fahim Kawsar
Large Language Models (LLMs) have demonstrated remarkable generalization across diverse tasks, leading individuals to increasingly use them as personal assistants and universal com…
CroSSL: Cross-modal Self-Supervised Learning for Time-series through Latent Masking
Shohreh Deldari, Dimitris Spathis, Mohammad Malekzadeh +3
Limited availability of labeled data for machine learning on multimodal time-series extensively hampers progress in the field. Self-supervised learning (SSL) is a promising approac…
Kaizen: Practical Self-supervised Continual Learning with Continual Fine-tuning
Chi Ian Tang, Lorena Qendro, Dimitris Spathis +3
Self-supervised learning (SSL) has shown remarkable performance in computer vision tasks when trained offline. However, in a Continual Learning (CL) scenario where new data is intr…
Enhancing Efficiency in Multidevice Federated Learning through Data Selection
Fan Mo, Mohammad Malekzadeh, Soumyajit Chatterjee +2
Ubiquitous wearable and mobile devices provide access to a diverse set of data. However, the mobility demand for our devices naturally imposes constraints on their computational an…
Orchestra: Unsupervised Federated Learning via Globally Consistent Clustering
Ekdeep Singh Lubana, Chi Ian Tang, Fahim Kawsar +2
Federated learning is generally used in tasks where labels are readily available (e.g., next word prediction). Relaxing this constraint requires design of unsupervised learning tec…
FLAME: Federated Learning Across Multi-device Environments
Hyunsung Cho, Akhil Mathur, Fahim Kawsar
Federated Learning (FL) enables distributed training of machine learning models while keeping personal data on user devices private. While we witness increasing applications of FL…
ColloSSL: Collaborative Self-Supervised Learning for Human Activity Recognition
Yash Jain, Chi Ian Tang, Chulhong Min +2
A major bottleneck in training robust Human-Activity Recognition models (HAR) is the need for large-scale labeled sensor datasets. Because labeling large amounts of sensor data is…
Tiny, always-on and fragile: Bias propagation through design choices in on-device machine learning workflows
Wiebke Toussaint, Aaron Yi Ding, Fahim Kawsar +1
Billions of distributed, heterogeneous and resource constrained IoT devices deploy on-device machine learning (ML) for private, fast and offline inference on personal data. On-devi…
FRuDA: Framework for Distributed Adversarial Domain Adaptation
Shaoduo Gan, Akhil Mathur, Anton Isopoussu +3
Breakthroughs in unsupervised domain adaptation (uDA) can help in adapting models from a label-rich source domain to unlabeled target domains. Despite these advancements, there is…
SensiX++: Bringing MLOPs and Multi-tenant Model Serving to Sensory Edge Devices
Chulhong Min, Akhil Mathur, Utku Gunay Acer +2
We present SensiX++ - a multi-tenant runtime for adaptive model execution with integrated MLOps on edge devices, e.g., a camera, a microphone, or IoT sensors. SensiX++ operates on…