Mahdi Morafah

18 papers A* 2A 1Journal 14Unranked 1
YearRankTypeTitle / Venue / Authors
2025 J jnl
Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data.
CoRR
Abhijit Chunduru, Majid Morafah, Mahdi Morafah, Vishnu Pandi Chellapandi, Ang Li
2025 J jnl
Federated Learning Client Pruning for Noisy Labels.
ACM Trans. Model. Perform. Evaluation Comput. Syst.
Mahdi Morafah, Hojin Chang, Chen Chen, Bill Lin
2024 J jnl
A Practical Recipe for Federated Learning Under Statistical Heterogeneity Experimental Design.
IEEE Trans. Artif. Intell.
Mahdi Morafah, Weijia Wang, Bill Lin
2024 J jnl
Federated Learning Client Pruning for Noisy Labels.
CoRR
Mahdi Morafah, Hojin Chang, Chen Chen, Bill Lin
2024 A conf
Large Scale Delocalized Federated Learning Over a Huge Diversity of Devices in Emerging Next-Generation Edge Intelligence Environments.
ICCAD
Mahdi Morafah, Hojin Chang, Bill Lin
2024 J jnl
Rethinking Data Heterogeneity in Federated Learning: Introducing a New Notion and Standard Benchmarks.
IEEE Trans. Artif. Intell.
Saeed Vahidian, Mahdi Morafah, Chen Chen, Mubarak Shah, Bill Lin
2024 J jnl
Stable Diffusion-based Data Augmentation for Federated Learning with Non-IID Data.
CoRR
Mahdi Morafah, Matthias Reisser, Bill Lin, Christos Louizos
2024 A* conf
Towards Diverse Device Heterogeneous Federated Learning via Task Arithmetic Knowledge Integration.
NeurIPS
Mahdi Morafah, Vyacheslav Kungurtsev, Hojin Chang, Chen Chen, Bill Lin
2024 J jnl
Towards Diverse Device Heterogeneous Federated Learning via Task Arithmetic Knowledge Integration.
CoRR
Mahdi Morafah, Vyacheslav Kungurtsev, Hojin Chang, Chen Chen, Bill Lin
2023 J jnl
A Practical Recipe for Federated Learning Under Statistical Heterogeneity Experimental Design.
CoRR
Mahdi Morafah, Weijia Wang, Bill Lin
2023 J jnl
Decentralized Asynchronous Nonconvex Stochastic Optimization on Directed Graphs.
IEEE Trans. Control. Netw. Syst.
Vyacheslav Kungurtsev, Mahdi Morafah, Tara Javidi, Gesualdo Scutari
2023 A* conf
Efficient Distribution Similarity Identification in Clustered Federated Learning via Principal Angles between Client Data Subspaces.
AAAI
Saeed Vahidian, Mahdi Morafah, Weijia Wang, Vyacheslav Kungurtsev, Chen Chen, Mubarak Shah, Bill Lin
2023 J jnl
FLIS: Clustered Federated Learning Via Inference Similarity for Non-IID Data Distribution.
IEEE Open J. Comput. Soc.
Mahdi Morafah, Saeed Vahidian, Weijia Wang, Bill Lin
2022 J jnl
Efficient Distribution Similarity Identification in Clustered Federated Learning via Principal Angles Between Client Data Subspaces.
CoRR
Saeed Vahidian, Mahdi Morafah, Weijia Wang, Vyacheslav Kungurtsev, Chen Chen, Mubarak Shah, Bill Lin
2022 J jnl
FLIS: Clustered Federated Learning via Inference Similarity for Non-IID Data Distribution.
CoRR
Mahdi Morafah, Saeed Vahidian, Weijia Wang, Bill Lin
2022 J jnl
Rethinking Data Heterogeneity in Federated Learning: Introducing a New Notion and Standard Benchmarks.
CoRR
Mahdi Morafah, Saeed Vahidian, Chen Chen, Mubarak Shah, Bill Lin
2021 — conf
Personalized Federated Learning by Structured and Unstructured Pruning under Data Heterogeneity.
ICDCS Workshops
Saeed Vahidian, Mahdi Morafah, Bill Lin
2021 J jnl
Personalized Federated Learning by Structured and Unstructured Pruning under Data Heterogeneity.
CoRR
Saeed Vahidian, Mahdi Morafah, Bill Lin
scripts/setup-and-run.sh
← Index scripts/setup-and-run.sh bash 
#!/bin/bash
set -e

# Setup Binary Ninja Python API if available on host (from snapshot)
if [ -d "/opt/binaryninja" ] && [ -f "/opt/binaryninja/scripts/linux-setup.sh" ]; then
    echo "Binary Ninja found on host, setting up Python API..."
    cd /opt
    ./binaryninja/scripts/linux-setup.sh -s || echo "Binary Ninja setup failed"
    
    # Change back to the app directory
    cd /app
    
    # Verify installation
    python3 -c "import binaryninja; print('Binary Ninja Python API ready, version:', binaryninja.core_version())" 2>/dev/null || echo "Binary Ninja Python API not available"
else
    echo "Binary Ninja not found on host - decompilation will be disabled"
fi

# Copy license if available
if [ -f "/opt/binaryninja-license/license.dat" ]; then
    mkdir -p ~/.binaryninja
    cp /opt/binaryninja-license/license.dat ~/.binaryninja/
    echo "Binary Ninja license configured"
fi

# Execute the original command
exec "$@"