Danner, Gábor

PhD in Computer Science Thesis Researcher University of Szeged gabor.danner [at] gmail.com

Research

• Backdoors in deep neural networks
• Árpád Berta, Gábor Danner, István Hegedűs, and Márk Jelasity: Hiding needles in a haystack: Towards constructing neural networks that evade verification.
  In Proceedings of the 2022 ACM Workshop on Information Hiding and Multimedia Security (IH & MMSec'22), pages 51–62, New York, NY, USA, 2022. ACM. (doi:10.1145/3531536.3532966)
• Decentralized data mining
• Gábor Danner, István Hegedűs, and Márk Jelasity: Improving gossip learning via limited model merging.
  In Ngoc Thanh Nguyen, János Botzheim, László Gulyás, Manuel Nunez, Jan Treur, Gottfried Vossen, and Adrianna Kozierkiewicz, editors, Advances in Computational Collective Intelligence (ICCCI 2023), pages 351–363, Cham, 2023. Springer Nature Switzerland. (doi:10.1007/978-3-031-41774-0_28)
• István Hegedűs, Gábor Danner, and Márk Jelasity: Decentralized learning works: An empirical comparison of gossip learning and federated learning.
  Journal of Parallel and Distributed Computing, 148:109–124, February 2021. (doi:10.1016/j.jpdc.2020.10.006)
• Gábor Danner, István Hegedűs, and Márk Jelasity: Decentralized machine learning using compressed push-pull averaging.
  In Proceedings of the 1st International Workshop on Distributed Infrastructure for Common Good (DICG), pages 31–36. ACM, 2020. (doi:10.1145/3428662.3428792)
• István Hegedűs, Gábor Danner, and Márk Jelasity: Decentralized recommendation based on matrix factorization: A comparison of gossip and federated learning.
  In Peggy Cellier and Kurt Driessens, editors, ECML PKDD Workshops 2019, number 1167 in Communications in Computer and Information Science, pages 317–332. Springer Nature Switzerland AG, 2020. DMLE19. (doi:10.1007/978-3-030-43823-4_27)
• István Hegedűs, Gábor Danner, and Márk Jelasity: Gossip learning as a decentralized alternative to federated learning.
  In José Pereira and Laura Ricci, editors, Proceedings of the 19th IFIP International Conference on Distributed Applications and Interoperable Systems (DAIS 2019), volume 11534 of Lecture Notes in Computer Science, pages 74–90. Springer International Publishing, 2019. (doi:10.1007/978-3-030-22496-7_5)
• Gábor Danner and Márk Jelasity: Robust decentralized mean estimation with limited communication.
  In Marco Aldinucci, Luca Padovani, and Massimo Torquati, editors, Euro-Par 2018, volume 11014 of Lecture Notes in Computer Science, pages 447–461. Springer International Publishing, 2018. (doi:10.1007/978-3-319-96983-1_32)
• Gábor Danner and Márk Jelasity: Token account algorithms: The best of the proactive and reactive worlds.
  In Proceedings of The 38th International Conference on Distributed Computing Systems (ICDCS 2018), pages 885–895. IEEE Computer Society, 2018. (doi:10.1109/ICDCS.2018.00090)
• Gábor Danner, Árpád Berta, István Hegedűs, and Márk Jelasity: Robust fully distributed mini-batch gradient descent with privacy preservation.
  Security and Communication Networks, 2018:6728020, 2018. (doi:10.1155/2018/6728020)
• Gábor Danner and Márk Jelasity: Fully distributed privacy preserving mini-batch gradient descent learning.
  In Alysson Bessani and Sara Bouchenak, editors, Proceedings of the 15th IFIP International Conference on Distributed Applications and Interoperable Systems (DAIS 2015), volume 9038 of Lecture Notes in Computer Science, pages 30–44. Springer International Publishing, 2015. (doi:10.1007/978-3-319-19129-4_3)
• AI in games
  • See our dedicated website: Malom: Ultra-Strong and Extended Solutions for Nine Men's Morris, Morabaraba, and Lasker Morris

Oktatás

Aktuális

Régi

Véleményezés

Másik weblapom