collaborators

7 papers

cs.LG2026

Shapley Neuron Values for Continual Learning: Which Neurons Matter Most?

Mohammad Ali Vahedifar, Abhisek Ray, Qi Zhang

Continual learning enables neural networks to learn tasks sequentially without forgetting previously acquired knowledge. However, neural networks suffer from catastrophic forgettin…

cs.LG2026

No Forgetting Learning: Buffer-free Continual Learning Classification

Mohammad Ali Vahedifar, Qi Zhang

Most Continual Learning (CL) methods maintain performance on earlier tasks by storing exemplars in a replay buffer, introducing memory overhead that scales with the number of tasks…

eess.SP2026

Continuous Orthogonal Mode Decomposition: Haptic Signal Prediction in Tactile Internet

Mohammad Ali Vahedifar, Mojtaba Nazari, Qi Zhang

The Tactile Internet demands sub-millisecond latency and ultra-high reliability, as even slight latency or packet loss can destabilize haptic control. To address this, we propose t…

eess.SP2026

Discrete Mode Decomposition Meets Shapley Value: Robust Signal Prediction in Tactile Internet

Mohammad Ali Vahedifar, Qi Zhang

Tactile Internet (TI) requires ultra-low latency and high reliability to ensure stability and transparency in touch-enabled teleoperation. However, variable delays and packet loss…

eess.SP2026

Shapley Features for Robust Signal Prediction in Tactile Internet

Mohammad Ali Vahedifar, Qi Zhang

The Tactile Internet (TI) requires ultra-low latency and reliable haptic signal transmission, yet packet loss and delay remain unresolved challenges. We present a novel prediction…

eess.SP2025

Signal Prediction for Loss Mitigation in Tactile Internet: A Leader-Follower Game-Theoretic Approach

Mohammad Ali Vahedifar, Qi Zhang

Tactile Internet (TI) requires achieving ultra-low latency and highly reliable packet delivery for haptic signals. In the presence of packet loss and delay, the signal prediction m…