Conference PaperBayesian Graph Neural Networks with Adaptive Connection SamplingHasanzadeh, Arman; Hajiramezanali, Ehsan; Boluki, Shahin; Zhou, Mingyuan; Duffield, Nick; Narayanan, Krishna; Qian, XiaoningnullWe propose a unified framework for adap- tive connection sampling in graph neural net- works (GNNs) that generalizes existing stochas- tic regularization methods for training GNNs. The proposed framework not only alleviates over- smoothing and over-fitting tendencies of deep GNNs, but also enables learning with uncertainty in graph analytic tasks with GNNs. Instead of using fixed sampling rates or hand-tuning them as model hyperparameters as in existing stochas- tic regularization methods, our adaptive connec- tion sampling can be trained jointly with GNN model parameters in both global and local fash- ions. GNN training with adaptive connection sampling is shown to be mathematically equiv- alent to an efficient approximation of training Bayesian GNNs. Experimental results with abla- tion studies on benchmark datasets validate that adaptively learning the sampling rate given graph training data is the key to boosting the perfor- mance of GNNs in semi-supervised node classifi- cation, making them less prone to over-smoothing and over-fitting with more robust prediction.2020-01-0110209364International Conference on Machine Learning37https://doi.org/1934904; 1839816; 1848596National Science Foundation