The approximate personalized propagation of neural predictions layer from the "Predict then Propagate: Graph Neural Networks meet Personalized PageRank" paper. A sampling algorithm from the "PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space" paper, which iteratively samples the most distant point with regard to the rest points.

Memory based pooling layer from "Memory-Based Graph Networks" paper, which learns a coarsened graph representation based on soft cluster assignments. Applies Batch Normalization over a 5D input (a mini-batch of 3D inputs with additional channel dimension) as described in the paper Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift .Furthermore, an interesting discussion concerns the trade-off between representational power (usually gained through learnable functions implemented as neural networks) and the formal property of permutation invariance ( Buterez et al.

The PointGNN operator from the "Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloud" paper.For example, mean aggregation captures the distribution (or proportions) of elements, max aggregation proves to be advantageous to identify representative elements, and sum aggregation enables the learning of structural graph properties ( Xu et al. The graph convolutional operator with initial residual connections and identity mapping (GCNII) from the "Simple and Deep Graph Convolutional Networks" paper. Applies Graph Size Normalization over each individual graph in a batch of node features as described in the "Benchmarking Graph Neural Networks" paper. During training, randomly zeroes some of the elements of the input tensor with probability p using samples from a Bernoulli distribution.

The PPFNet operator from the "PPFNet: Global Context Aware Local Features for Robust 3D Point Matching" paper.Creates a criterion that measures the loss given inputs x 1 x1 x 1, x 2 x2 x 2, two 1D mini-batch or 0D Tensors, and a label 1D mini-batch or 0D Tensor y y y (containing 1 or -1). The pathfinder discovery network convolutional operator from the "Pathfinder Discovery Networks for Neural Message Passing" paper. Applies batch normalization over a batch of features as described in the "Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift" paper. The Adversarially Regularized Variational Graph Auto-Encoder model from the "Adversarially Regularized Graph Autoencoder for Graph Embedding" paper. A greedy clustering algorithm from the "Weighted Graph Cuts without Eigenvectors: A Multilevel Approach" paper of picking an unmarked vertex and matching it with one of its unmarked neighbors (that maximizes its edge weight).

Conv1d module with lazy initialization of the in_channels argument of the Conv1d that is inferred from the input. Applies the log ⁡ ( Softmax ( x ) ) \log(\text{Softmax}(x)) lo g ( Softmax ( x )) function to an n-dimensional input Tensor. The Efficient Graph Convolution from the "Adaptive Filters and Aggregator Fusion for Efficient Graph Convolutions" paper. The graph attentional propagation layer from the "Attention-based Graph Neural Network for Semi-Supervised Learning" paper.

The edge pooling operator from the "Towards Graph Pooling by Edge Contraction" and "Edge Contraction Pooling for Graph Neural Networks" papers.