Institution profile

Tarbiat Modares University

Academic institutionasia · ir
Official website
Research library22linked papers
Opportunities0open roles
Selected work

Representative Papers

ProCAVE: A Self-Adaptive, Full-Lifecycle Edge Caching Framework for Video Streaming via Predictive Bandwidth Estimation and Preference-Aware Deep Reinforcement Learning

Aug 04, 2026

This work addresses the insufficient coordination between edge caching and adaptive bitrate (ABR) streaming caused by wireless bandwidth fluctuations and diverse user preferences. To this end, the authors propose an end-to-end adaptive edge caching framework that jointly models predictive bandwidth estimation, PPO-driven ABR decisions, and DDPG-based continuous cache control, enabling proactive bitrate selection and user-aware cache optimization. A lightweight Transformer architecture is employed for throughput prediction, facilitating efficient coordination under high-dimensional global states. Experimental evaluation using MovieLens user preference data and real-world Ghent 4G bandwidth traces demonstrates that the proposed approach significantly improves byte hit rate, reduces backhaul load, and outperforms baseline methods such as FlyCache, achieving substantial gains in Quality of Experience (QoE) metrics.

0 citationsRead paper

Multimodal Survival Modeling and Fairness-Aware Clinical Machine Learning for 5-Year Breast Cancer Risk Prediction

Feb 25, 2026

This study addresses common challenges in clinical risk prediction models—such as poor calibration, limited generalizability, and subgroup bias—when applied to high-dimensional multimodal breast cancer data. The authors propose a governance-oriented, reproducible multimodal survival modeling framework that integrates clinical variables, transcriptomic profiles, and copy number variation features. The pipeline incorporates variance- and sparsity-based filtering, dimensionality reduction, and survival modeling via CoxNet (an elastic net–regularized Cox model) and XGBoost gradient-boosted survival trees, with rigorous hyperparameter optimization. Emphasizing calibration, fairness, robustness, and reproducibility, the framework achieves time-dependent AUCs of 96.6% and 92.5% for five-year survival prediction. Fairness audits further demonstrate stable performance across diverse clinical subgroups.

0 citationsRead paper

TinyGuard:A lightweight Byzantine Defense for Resource-Constrained Federated Learning via Statistical Update Fingerprints

Feb 02, 2026

This work addresses the high computational overhead of existing Byzantine-robust aggregation methods, which hinders their deployment in resource-constrained, large-scale federated learning systems. To overcome this limitation, the authors propose a lightweight Byzantine detection mechanism termed “Statistical Handcuffs,” which operates within the standard FedAvg framework. By extracting low-dimensional statistical fingerprints—such as update norms, inter-layer ratios, sparsity, and low-order moments—from client updates, the method constructs a detection space without modifying the underlying optimization process. This design ensures that adversaries cannot simultaneously evade detection and effectively poison the model. The approach is architecture-agnostic and particularly well-suited for LoRA-based federated fine-tuning. Experimental results demonstrate that under extreme non-IID settings with 50–150 clients and various attack types, the model maintains over 95% accuracy while achieving a stable detection precision of 0.8.

0 citationsRead paper
Recent publications

Latest Papers

ProCAVE: A Self-Adaptive, Full-Lifecycle Edge Caching Framework for Video Streaming via Predictive Bandwidth Estimation and Preference-Aware Deep Reinforcement Learning

Aug 04, 2026

This work addresses the insufficient coordination between edge caching and adaptive bitrate (ABR) streaming caused by wireless bandwidth fluctuations and diverse user preferences. To this end, the authors propose an end-to-end adaptive edge caching framework that jointly models predictive bandwidth estimation, PPO-driven ABR decisions, and DDPG-based continuous cache control, enabling proactive bitrate selection and user-aware cache optimization. A lightweight Transformer architecture is employed for throughput prediction, facilitating efficient coordination under high-dimensional global states. Experimental evaluation using MovieLens user preference data and real-world Ghent 4G bandwidth traces demonstrates that the proposed approach significantly improves byte hit rate, reduces backhaul load, and outperforms baseline methods such as FlyCache, achieving substantial gains in Quality of Experience (QoE) metrics.

0 citationsRead paper

Multimodal Survival Modeling and Fairness-Aware Clinical Machine Learning for 5-Year Breast Cancer Risk Prediction

Feb 25, 2026

This study addresses common challenges in clinical risk prediction models—such as poor calibration, limited generalizability, and subgroup bias—when applied to high-dimensional multimodal breast cancer data. The authors propose a governance-oriented, reproducible multimodal survival modeling framework that integrates clinical variables, transcriptomic profiles, and copy number variation features. The pipeline incorporates variance- and sparsity-based filtering, dimensionality reduction, and survival modeling via CoxNet (an elastic net–regularized Cox model) and XGBoost gradient-boosted survival trees, with rigorous hyperparameter optimization. Emphasizing calibration, fairness, robustness, and reproducibility, the framework achieves time-dependent AUCs of 96.6% and 92.5% for five-year survival prediction. Fairness audits further demonstrate stable performance across diverse clinical subgroups.

0 citationsRead paper

TinyGuard:A lightweight Byzantine Defense for Resource-Constrained Federated Learning via Statistical Update Fingerprints

Feb 02, 2026

This work addresses the high computational overhead of existing Byzantine-robust aggregation methods, which hinders their deployment in resource-constrained, large-scale federated learning systems. To overcome this limitation, the authors propose a lightweight Byzantine detection mechanism termed “Statistical Handcuffs,” which operates within the standard FedAvg framework. By extracting low-dimensional statistical fingerprints—such as update norms, inter-layer ratios, sparsity, and low-order moments—from client updates, the method constructs a detection space without modifying the underlying optimization process. This design ensures that adversaries cannot simultaneously evade detection and effectively poison the model. The approach is architecture-agnostic and particularly well-suited for LoRA-based federated fine-tuning. Experimental results demonstrate that under extreme non-IID settings with 50–150 clients and various attack types, the model maintains over 95% accuracy while achieving a stable detection precision of 0.8.

0 citationsRead paper