### About this deal

The graph neural network operator from the "Convolutional Networks on Graphs for Learning Molecular Fingerprints" paper. The Frequency Adaptive Graph Convolution operator from the "Beyond Low-Frequency Information in Graph Convolutional Networks" paper. Performs aggregations with one or more aggregators and combines aggregated results, as described in the "Principal Neighbourhood Aggregation for Graph Nets" and "Adaptive Filters and Aggregator Fusion for Efficient Graph Convolutions" papers. 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 graph convolutional operator with initial residual connections and identity mapping (GCNII) from the "Simple and Deep Graph Convolutional Networks" paper. The Batch Representation Orthogonality penalty from the "Improving Molecular Graph Neural Network Explainability with Orthonormalization and Induced Sparsity" paper. Applies the gated linear unit function G L U ( a , b ) = a ⊗ σ ( b ) {GLU}(a, b)= a \otimes \sigma(b) G LU ( a , b ) = a ⊗ σ ( b ) where a a a is the first half of the input matrices and b b b is the second half.g., the j j j-th channel of the i i i-th sample in the batched input is a 2D tensor input [ i , j ] \text{input}[i, j] input [ i , j ]). Importantly, MultiAggregation provides various options to combine the outputs of its underlying aggegations ( e.

e. its supervised RECT-L part, from the "Network Embedding with Completely-imbalanced Labels" paper. The simple spectral graph convolutional operator from the "Simple Spectral Graph Convolution" paper. The Gini coefficient from the "Improving Molecular Graph Neural Network Explainability with Orthonormalization and Induced Sparsity" paper. Creates a criterion that optimizes a multi-class classification hinge loss (margin-based loss) between input x x x (a 2D mini-batch Tensor) and output y y y (which is a 1D tensor of target class indices, 0 ≤ y ≤ x.Applies the log ( Softmax ( x ) ) \log(\text{Softmax}(x)) lo g ( Softmax ( x )) function to an n-dimensional input Tensor. GAT class GAT ( in_channels : int, hidden_channels : int, num_layers : int, out_channels : Optional [ int ] = None, dropout : float = 0.

The dynamic edge convolutional operator from the "Dynamic Graph CNN for Learning on Point Clouds" paper (see torch_geometric.Creates a criterion that optimizes a multi-class multi-classification hinge loss (margin-based loss) between input x x x (a 2D mini-batch Tensor) and output y y y (which is a 2D Tensor of target class indices). Applies instance normalization over each individual example in a batch of node features as described in the "Instance Normalization: The Missing Ingredient for Fast Stylization" paper. num_features , 64 ), 'x, edge_index -> x1' ), ReLU ( inplace = True ), ( GCNConv ( 64 , 64 ), 'x1, edge_index -> x2' ), ReLU ( inplace = True ), ( lambda x1 , x2 : [ x1 , x2 ], 'x1, x2 -> xs' ), ( JumpingKnowledge ( "cat" , 64 , num_layers = 2 ), 'xs -> x' ), ( global_mean_pool , 'x, batch -> x' ), Linear ( 2 * 64 , dataset . Memory based pooling layer from "Memory-Based Graph Networks" paper, which learns a coarsened graph representation based on soft cluster assignments. Applies the Softmax function to an n-dimensional input Tensor rescaling them so that the elements of the n-dimensional output Tensor lie in the range [0,1] and sum to 1.

The Jumping Knowledge layer aggregation module from the "Representation Learning on Graphs with Jumping Knowledge Networks" paper. Creates a criterion that optimizes a two-class classification logistic loss between input tensor x x x and target tensor y y y (containing 1 or -1). Applies the Softplus function Softplus ( x ) = 1 β ∗ log ( 1 + exp ( β ∗ x ) ) \text{Softplus}(x) = \frac{1}{\beta} * \log(1 + \exp(\beta * x)) Softplus ( x ) = β 1 ∗ lo g ( 1 + exp ( β ∗ x )) element-wise. The Weisfeiler Lehman (WL) operator from the "A Reduction of a Graph to a Canonical Form and an Algebra Arising During this Reduction" paper. The Deep Graph Infomax model from the "Deep Graph Infomax" paper based on user-defined encoder and summary model \(\mathcal{E}\) and \(\mathcal{R}\) respectively, and a corruption function \(\mathcal{C}\).The path integral based convolutional operator from the "Path Integral Based Convolution and Pooling for Graph Neural Networks" paper. The softmax aggregation operator based on a temperature term, as described in the "DeeperGCN: All You Need to Train Deeper GCNs" paper. Applies Batch Normalization over a 4D input (a mini-batch of 2D inputs with additional channel dimension) as described in the paper Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift .