MLSP-L18.6
ACTIVATION COMPRESSION OF GRAPH NEURAL NETWORKS USING BLOCK-WISE QUANTIZATION WITH IMPROVED VARIANCE MINIMIZATION
Sebastian Eliassen, Raghavendra Selvan, University of Copenhagen, Denmark
Session:
MLSP-L18: Graph Neural Networks II Lecture
Track:
Machine Learning for Signal Processing
Location:
Room 102
Presentation Time:
Thu, 18 Apr, 18:10 - 18:30 (UTC +9)
Session Co-Chairs:
Raghavendra Selvan, University of Copenhagen and Shixiong Zhang, Capital One
Session MLSP-L18
MLSP-L18.1: Bregman Graph Neural Network
Jiayu Zhai, Lequan Lin, Dai Shi, Junbin Gao, The University of Sydney, Australia
MLSP-L18.2: ENHANCING PERFORMANCE OF COARSENED GRAPHS WITH GRADIENT-MATCHING
Wenjie Yang, Shengzhong Zhang, Zengfeng Huang, Fudan University, China
MLSP-L18.3: Graph Convolutional Neural Networks in the Companion Model
John Shi, Shreyas Chaudhari, Jose Moura, Carnegie Mellon University, United States of America
MLSP-L18.4: GLMAE: GRAPH REPRESENTATION LEARNING METHOD COMBINING GENERATIVE LEARNING AND MASKING AUTOENCODER
Yunfeng Xu, Shaohui Zhao, Hexun Fan, Jialin Wang, Hebei University of Science and Technology, China
MLSP-L18.5: NOISE-DISENTANGLED GRAPH CONTRASTIVE LEARNING VIA LOW-RANK AND SPARSE SUBSPACE DECOMPOSITION
Gehang Zhang, Jiawei Sheng, Shicheng Wang, Tingwen Liu, Institute of Information Engineering, Chinese Academy of Sciences, China
MLSP-L18.6: ACTIVATION COMPRESSION OF GRAPH NEURAL NETWORKS USING BLOCK-WISE QUANTIZATION WITH IMPROVED VARIANCE MINIMIZATION
Sebastian Eliassen, Raghavendra Selvan, University of Copenhagen, Denmark
Contacts