Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective

Kaidi Xu, Hongge Chen, Sijia Liu, +4

EngineeringMachine LearningNetwork RobustnessNetwork AnalysisGraph Processing +16

PCONV: The Missing but Desirable Sparsity in DNN Weight Pruning for Real-Time Execution on Mobile Devices

Xiaolong Ma, Fu-Ming Guo, Wei Niu, +5

Proceedings of the AAAI Conference on Artificial Intelligence

Convolutional Neural NetworkEngineeringMachine LearningDnn WeightComputer Architecture +15

ADMM-NN

Ao Ren, Tianyun Zhang, Shaokai Ye, +5

EngineeringMachine LearningHardware AccelerationAdmm IterationSparse Neural Network +9

Mix and Match: A Novel FPGA-Centric Deep Neural Network Quantization Framework

Sung-En Chang, Yanyu Li, Mengshu Sun, +5

Artificial IntelligenceEngineeringMachine LearningHardware AlgorithmComputer Architecture +15

Structured Adversarial Attack: Towards General Implementation and Better Interpretability

Kaidi Xu, Sijia Liu, Pu Zhao, +6

arXiv (Cornell University)

EngineeringMachine LearningAdversarial AttackInformation SecurityAutoencoders +14

Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Neural Network Robustness Verification

Shiqi Wang, Huan Zhang, Kaidi Xu, +4

Neural Information Processing Systems

Mathematical ProgrammingPer-neuron Split ConstraintsMachine LearningEngineeringComputational Neuroscience +8

Automatic Perturbation Analysis for Scalable Certified Robustness and Beyond

Kaidi Xu, Zhouxing Shi, Huan Zhang, +6

arXiv (Cornell University)

Convolutional Neural NetworkPerturbation AnalysisMachine LearningEngineeringVerification +22

Non-Structured DNN Weight Pruning—Is It Beneficial in Any Platform?

Xiaolong Ma, Sheng Lin, Shaokai Ye, +10

IEEE Transactions on Neural Networks and Learning Systems

Any PlatformWeight QuantizationEngineeringMachine LearningHardware Acceleration +10

Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective

Kaidi Xu, Hongge Chen, Sijia Liu, +4

arXiv (Cornell University)

EngineeringMachine LearningNetwork RobustnessNetwork AnalysisGraph Processing +16

FILM-QNN: Efficient FPGA Acceleration of Deep Neural Networks with Intra-Layer, Mixed-Precision Quantization

Mengshu Sun, Zhengang Li, Alec Lu, +5

EngineeringMachine LearningHardware AlgorithmComputer ArchitectureFpga Devices +15