arXiv subjects

Reza Rahimi Azghan

Publications and source records attributed to Reza Rahimi Azghan.

7 recordsLinked to original sources

arXiv2026

Latent-LoRA: Compact Latent-Space Adapters with Gradient-Free Routing for Continual Learning

Large language models generalize well to individual tasks but lack an inherent mechanism for learning them sequentially, leading to catastrophic forgetting. To mitigate this, LoRA-based continual learning methods allocate a separate low-rank adapter per task, yet existing approaches either require task identity at inference or sum all adapters indiscriminately, letting irrelevant branches distort the output. Recent gating-based solutions route inputs to the correct adapter but introduce trainable parameters that themselves need protection against forgetting. In this work, we observe that pooled token embeddings from a frozen LLM embedding layer already separate task distributions throughout the learning sequence. A Gaussian mixture model fitted on these embeddings, without any gradient-based training, is sufficient for task-agnostic adapter selection at test time. This eliminates the need for a learned gating module. On the adapter side, constraining each task's parameters to the principal subspace of the pretrained weights via SVD yields a compact latent-space parameterization. Within this subspace, orthogonal regularization directly controls inter-task interference. The resulting system, Latent-LoRA, is replay-free, requires no trainable routing component, and uses substantially fewer parameters per task. Experiments across five model scales and two established continual learning benchmarks show state-of-the-art performance with near-zero forgetting.

cs.LG↗

arXiv2026

Gated Adaptation for Continual Learning in Human Activity Recognition

Wearable sensors in Internet of Things (IoT) ecosystems increasingly support applications such as remote health monitoring, elderly care, and smart home automation, all of which rely on robust human activity recognition (HAR). Continual learning systems must balance plasticity (learning new tasks) with stability (retaining prior knowledge), yet AI models often exhibit catastrophic forgetting, where learning new tasks degrades performance on earlier ones. This challenge is especially acute in domain-incremental HAR, where on-device models must adapt to new subjects with distinct movement patterns while maintaining accuracy on prior subjects without transmitting sensitive data to the cloud. We propose a parameter-efficient continual learning framework based on channel-wise gated modulation of frozen pretrained representations. Our key insight is that adaptation should operate through feature selection rather than feature generation: by restricting learned transformations to diagonal scaling of existing features, we preserve the geometry of pretrained representations while enabling subject-specific modulation. We provide a theoretical analysis showing that gating implements a bounded diagonal operator that limits representational drift compared to unconstrained linear transformations. Empirically, freezing the backbone substantially reduces forgetting, and lightweight gates restore lost adaptation capacity, achieving stability and plasticity simultaneously. On PAMAP2 with 8 sequential subjects, our approach reduces forgetting from 39.7% to 16.2% and improves final accuracy from 56.7% to 77.7%, while training less than 2% of parameters. Our method matches or exceeds standard continual learning baselines without replay buffers or task-specific regularization, confirming that structured diagonal operators are effective and efficient under distribution shift.

cs.LG↗

arXiv2025

CLAD-Net: Continual Activity Recognition in Multi-Sensor Wearable Systems

The rise of deep learning has greatly advanced human behavior monitoring using wearable sensors, particularly human activity recognition (HAR). While deep models have been widely studied, most assume stationary data distributions - an assumption often violated in real-world scenarios. For example, sensor data from one subject may differ significantly from another, leading to distribution shifts. In continual learning, this shift is framed as a sequence of tasks, each corresponding to a new subject. Such settings suffer from catastrophic forgetting, where prior knowledge deteriorates as new tasks are learned. This challenge is compounded by the scarcity and inconsistency of labeled data in human studies. To address these issues, we propose CLAD-Net (Continual Learning with Attention and Distillation), a framework enabling wearable-sensor models to be updated continuously without sacrificing performance on past tasks. CLAD-Net integrates a self-supervised transformer, acting as long-term memory, with a supervised Convolutional Neural Network (CNN) trained via knowledge distillation for activity classification. The transformer captures global activity patterns through cross-attention across body-mounted sensors, learning generalizable representations without labels. Meanwhile, the CNN leverages knowledge distillation to retain prior knowledge during subject-wise fine-tuning. On PAMAP2, CLAD-Net achieves 91.36 percent final accuracy with only 8.78 percent forgetting, surpassing memory-based and regularization-based baselines such as Experience Replay and Elastic Weight Consolidation. In semi-supervised settings with only 10-20 percent labeled data, CLAD-Net still delivers strong performance, demonstrating robustness to label scarcity. Ablation studies further validate each module's contribution.

cs.LG↗

arXiv2025

GluMind: Multimodal Parallel Attention and Knowledge Retention for Robust Cross-Population Blood Glucose Forecasting

This paper proposes GluMind, a transformer-based multimodal framework designed for continual and long-term blood glucose forecasting. GluMind devises two attention mechanisms, including cross-attention and multi-scale attention, which operate in parallel and deliver accurate predictive performance. Cross-attention effectively integrates blood glucose data with other physiological and behavioral signals such as activity, stress, and heart rate, addressing challenges associated with varying sampling rates and their adverse impacts on robust prediction. Moreover, the multi-scale attention mechanism captures long-range temporal dependencies. To mitigate catastrophic forgetting, GluMind incorporates a knowledge retention technique into the transformer-based forecasting model. The knowledge retention module not only enhances the model's ability to retain prior knowledge but also boosts its overall forecasting performance. We evaluate GluMind on the recently released AIREADI dataset, which contains behavioral and physiological data collected from healthy people, individuals with prediabetes, and those with type 2 diabetes. We examine the performance stability and adaptability of GluMind in learning continuously as new patient cohorts are introduced. Experimental results show that GluMind consistently outperforms other state-of-the-art forecasting models, achieving approximately 15% and 9% improvements in root mean squared error (RMSE) and mean absolute error (MAE), respectively.

cs.LG↗

arXiv2025

CAN-STRESS: A Real-World Multimodal Dataset for Understanding Cannabis Use, Stress, and Physiological Responses

Coping with stress is one of the most frequently cited reasons for chronic cannabis use. Therefore, it is hypothesized that cannabis users exhibit distinct physiological stress responses compared to non-users, and these differences would be more pronounced during moments of consumption. However, there is a scarcity of publicly available datasets that allow such hypotheses to be tested in real-world environments. This paper introduces a dataset named CAN-STRESS, collected using Empatica E4 wristbands. The dataset includes physiological measurements such as skin conductance, heart rate, and skin temperature from 82 participants (39 cannabis users and 43 non-users) as they went about their daily lives. Additionally, the dataset includes self-reported surveys where participants documented moments of cannabis consumption, exercise, and rated their perceived stress levels during those moments. In this paper, we publicly release the CAN-STRESS dataset, which we believe serves as a highly reliable resource for examining the impact of cannabis on stress and its associated physiological markers. I

q-bio.QM↗

arXiv2025

AttenGluco: Multimodal Transformer-Based Blood Glucose Forecasting on AI-READI Dataset

Diabetes is a chronic metabolic disorder characterized by persistently high blood glucose levels (BGLs), leading to severe complications such as cardiovascular disease, neuropathy, and retinopathy. Predicting BGLs enables patients to maintain glucose levels within a safe range and allows caregivers to take proactive measures through lifestyle modifications. Continuous Glucose Monitoring (CGM) systems provide real-time tracking, offering a valuable tool for monitoring BGLs. However, accurately forecasting BGLs remains challenging due to fluctuations due to physical activity, diet, and other factors. Recent deep learning models show promise in improving BGL prediction. Nonetheless, forecasting BGLs accurately from multimodal, irregularly sampled data over long prediction horizons remains a challenging research problem. In this paper, we propose AttenGluco, a multimodal Transformer-based framework for long-term blood glucose prediction. AttenGluco employs cross-attention to effectively integrate CGM and activity data, addressing challenges in fusing data with different sampling rates. Moreover, it employs multi-scale attention to capture long-term dependencies in temporal data, enhancing forecasting accuracy. To evaluate the performance of AttenGluco, we conduct forecasting experiments on the recently released AIREADI dataset, analyzing its predictive accuracy across different subject cohorts including healthy individuals, people with prediabetes, and those with type 2 diabetes. Furthermore, we investigate its performance improvements and forgetting behavior as new cohorts are introduced. Our evaluations show that AttenGluco improves all error metrics, such as root mean square error (RMSE), mean absolute error (MAE), and correlation, compared to the multimodal LSTM model. AttenGluco outperforms this baseline model by about 10% and 15% in terms of RMSE and MAE, respectively.

cs.LG↗

arXiv2024

CUDLE: Learning Under Label Scarcity to Detect Cannabis Use in Uncontrolled Environments

Wearable sensor systems have demonstrated a great potential for real-time, objective monitoring of physiological health to support behavioral interventions. However, obtaining accurate labels in free-living environments remains difficult due to limited human supervision and the reliance on self-labeling by patients, making data collection and supervised learning particularly challenging. To address this issue, we introduce CUDLE (Cannabis Use Detection with Label Efficiency), a novel framework that leverages self-supervised learning with real-world wearable sensor data to tackle a pressing healthcare challenge: the automatic detection of cannabis consumption in free-living environments. CUDLE identifies cannabis consumption moments using sensor-derived data through a contrastive learning framework. It first learns robust representations via a self-supervised pretext task with data augmentation. These representations are then fine-tuned in a downstream task with a shallow classifier, enabling CUDLE to outperform traditional supervised methods, especially with limited labeled data. To evaluate our approach, we conducted a clinical study with 20 cannabis users, collecting over 500 hours of wearable sensor data alongside user-reported cannabis use moments through EMA (Ecological Momentary Assessment) methods. Our extensive analysis using the collected data shows that CUDLE achieves a higher accuracy of 73.4%, compared to 71.1% for the supervised approach, with the performance gap widening as the number of labels decreases. Notably, CUDLE not only surpasses the supervised model while using 75% less labels, but also reaches peak performance with far fewer subjects.

cs.LG↗