Seguir
Dmitry Kazhdan
Dmitry Kazhdan
PhD Student at The University of Cambridge
Email confirmado em kazhdan.net
Título
Citado por
Citado por
Ano
Manipulating sgd with data ordering attacks
I Shumailov, Z Shumaylov, D Kazhdan, Y Zhao, N Papernot, MA Erdogdu, ...
Advances in Neural Information Processing Systems 34, 18021-18032, 2021
702021
Now You See Me (CME): Concept-based Model Extraction
D Kazhdan, B Dimanov, M Jamnik, P Liò, A Weller
29th International Conference on Information and Knowledge Management (CIKM …, 2020
662020
Gcexplainer: Human-in-the-loop concept-based explanations for graph neural networks
LC Magister, D Kazhdan, V Singh, P Liò
arXiv preprint arXiv:2107.11889, 2021
302021
MARLeME: A Multi-Agent Reinforcement Learning Model Extraction Library
D Kazhdan, Z Shams, P Liò
2020 International Joint Conference on Neural Networks (IJCNN), 2020
162020
Is Disentanglement all you need? Comparing Concept-based & Disentanglement Approaches
D Kazhdan, B Dimanov, HA Terre, M Jamnik, P Liò, A Weller
The Tenth International Conference on Learning Representations (ICLR 2021 …, 2021
152021
Encoding concepts in graph neural networks
LC Magister, P Barbiero, D Kazhdan, F Siciliano, G Ciravegna, F Silvestri, ...
arXiv preprint arXiv:2207.13586, 2022
142022
Towards robust metrics for concept representation evaluation
ME Zarlenga, P Barbiero, Z Shams, D Kazhdan, U Bhatt, A Weller, ...
Proceedings of the AAAI Conference on Artificial Intelligence 37 (10), 11791 …, 2023
132023
Algorithmic concept-based explainable reasoning
D Georgiev, P Barbiero, D Kazhdan, P Veličković, P Liò
Proceedings of the AAAI Conference on Artificial Intelligence 36 (6), 6685-6693, 2022
132022
MEME: Generating RNN Model Explanations via Model Extraction
D Kazhdan, B Dimanov, M Jamnik, P Liò
NeurIPS 2020, HAMLETS workshop, 2020
122020
Failing conceptually: Concept-based explanations of dataset shift
MA Wijaya, D Kazhdan, B Dimanov, M Jamnik
arXiv preprint arXiv:2104.08952, 2021
72021
Gci: A (g) raph (c) oncept (i) nterpretation framework
D Kazhdan, B Dimanov, LC Magister, P Barbiero, M Jamnik, P Lio
arXiv preprint arXiv:2302.04899, 2023
32023
Concept distillation in graph neural networks
LC Magister, P Barbiero, D Kazhdan, F Siciliano, G Ciravegna, F Silvestri, ...
World Conference on Explainable Artificial Intelligence, 233-255, 2023
22023
On the quality assurance of concept-based representations
ME Zarlenga, P Barbiero, Z Shams, D Kazhdan, U Bhatt, M Jamnik
22021
Explainer Divergence Scores (EDS): Some Post-Hoc Explanations May be Effective for Detecting Unknown Spurious Correlations
S Cardozo, GI Montero, D Kazhdan, B Dimanov, M Wijaya, M Jamnik, ...
arXiv preprint arXiv:2211.07650, 2022
2022
O sistema não pode efectuar a operação agora. Tente mais tarde.
Artigos 1–14