dhg.nn

Common Layers

dhg.nn.MLP

A Multi-Layer Perception (MLP) model.

Layers on Low-Order Structures

dhg.nn.GCNConv	The GCN convolution layer proposed in Semi-Supervised Classification with Graph Convolutional Networks paper (ICLR 2017).
dhg.nn.GraphSAGEConv	The GraphSAGE convolution layer proposed in Inductive Representation Learning on Large Graphs paper (NeurIPS 2017).
dhg.nn.GATConv	The GAT convolution layer proposed in Graph Attention Networks paper (ICLR 2018).
dhg.nn.GINConv	The GIN convolution layer proposed in How Powerful are Graph Neural Networks? paper (ICLR 2019).

Layers on High-Order Structures

dhg.nn.HGNNConv	The HGNN convolution layer proposed in Hypergraph Neural Networks paper (AAAI 2019).
dhg.nn.HGNNPConv	The HGNN + convolution layer proposed in HGNN+: General Hypergraph Neural Networks paper (IEEE T-PAMI 2022).
dhg.nn.JHConv	The Jump Hypergraph Convolution layer proposed in Dual Channel Hypergraph Collaborative Filtering paper (KDD 2020).
dhg.nn.HyperGCNConv	The HyperGCN convolution layer proposed in HyperGCN: A New Method of Training Graph Convolutional Networks on Hypergraphs paper (NeurIPS 2019).
dhg.nn.HNHNConv	The HNHN convolution layer proposed in HNHN: Hypergraph Networks with Hyperedge Neurons paper (ICML 2020).

Loss Functions

dhg.nn.BPRLoss

This criterion computes the Bayesian Personalized Ranking (BPR) loss between the positive scores and the negative scores.

Regularizations

dhg.nn.EmbeddingRegularization

Regularization function for embeddings.