MLSP-L16: Robustness and Trustworthy Machine Learning II
Thu, 18 Apr, 13:10 - 15:10 (UTC +9)
Location: Room 105
Session Type: Lecture
Session Co-Chairs: Dionysis Kalogerias, Yale University and Amit Ranjan Trivedi, University of Illinois at Chicago
Track: Machine Learning for Signal Processing
Click the to view the manuscript on IEEE Xplore Open Preview
Thu, 18 Apr, 13:10 - 13:30 (UTC +9)
 

MLSP-L16.1: FEDERATED LEARNING UNDER RESTRICTED USER AVAILABILITY
Periklis Theodoropoulos, Konstantinos Nikolakakis, Dionysis Kalogerias, Yale University, United States of America
Thu, 18 Apr, 13:30 - 13:50 (UTC +9)
 

MLSP-L16.2: CONFORMALIZED MULTIMODAL UNCERTAINTY REGRESSION AND REASONING
Domenico Parente, Nastaran Darabi, Alex Stutts, Theja Tulabandhula, Amit Ranjan Trivedi, University of Illinois at Chicago, United States of America
Thu, 18 Apr, 13:50 - 14:10 (UTC +9)
 

MLSP-L16.3: Fixed Inter-Neuron Covariability Induces Adversarial Robustness
Muhammad Shah, Bhiksha Raj, Carnegie Mellon University, United States of America
Thu, 18 Apr, 14:10 - 14:30 (UTC +9)
 

MLSP-L16.4: NOISE-BERT: A UNIFIED PERTURBATION-ROBUST FRAMEWORK WITH NOISE ALIGNMENT PRE-TRAINING FOR NOISY SLOT FILLING TASK
Jinxu Zhao, Guanting Dong, Yueyan Qiu, Tingfeng Hui, Xiaoshuai Song, Daichi Guo, Weiran Xu, Beijing University of Posts and Telecommunications, China
Thu, 18 Apr, 14:30 - 14:50 (UTC +9)
 

MLSP-L16.5: ANALYZING ADVERSARIAL VULNERABILITIES OF GRAPH LOTTERY TICKETS
Subhajit Dutta Chowdhury, Zhiyu Ni, Qingyuan Peng, University of Southern California, United States of America; Souvik Kundu, Intel Labs, United States of America; Pierluigi Nuzzo, University of Southern California, United States of America
Thu, 18 Apr, 14:50 - 15:10 (UTC +9)

MLSP-L16.6: Linearly-involved Moreau-Enhanced-over-Subspace Model: Debiased Sparse Modeling and Stable Outlier-Robust Regression
Masahiro Yukawa, Hiroyuki Kaneko, Kyohei Suzuki, Keio University, Japan; Isao Yamada, Tokyo Institute of Technology, Japan