Source code for pygod.detector.dmgd

# -*- coding: utf-8 -*-
""" Deep Multiclass Graph Description (DMGD)"""
# Author: Kay Liu <>
# License: BSD 2 clause

import torch
import warnings
from torch_geometric.nn import MLP, GCN

from . import DeepDetector
from ..nn import DMGDBase

[docs] class DMGD(DeepDetector): """ Deep Multiclass Graph Description DMGD is a support vector based multiclass outlier detector. Its backbone is an autoencoder that reconstructs the adjacency matrix of the graph with MSE loss and homophily loss. It applies k-means to cluster the nodes embedding and then uses support vector to detect outliers. See :cite:`bandyopadhyay2020integrating` for details. Parameters ---------- hid_dim : int, optional Hidden dimension of model. Default: ``64``. num_layers : int, optional Total number of layers in model. Default: ``2``. dropout : float, optional Dropout rate. Default: ``0.``. weight_decay : float, optional Weight decay (L2 penalty). Default: ``0.``. act : callable activation function or None, optional Activation function if not None. Default: ``torch.nn.functional.relu``. backbone : torch.nn.Module The backbone of the deep detector implemented in PyG. Default: ``torch_geometric.nn.GCN``. contamination : float, optional The amount of contamination of the dataset in (0., 0.5], i.e., the proportion of outliers in the dataset. Used when fitting to define the threshold on the decision function. Default: ``0.1``. lr : float, optional Learning rate. Default: ``0.004``. epoch : int, optional Maximum number of training epoch. Default: ``100``. gpu : int GPU Index, -1 for using CPU. Default: ``-1``. batch_size : int, optional Minibatch size, 0 for full batch training. Default: ``0``. num_neigh : int, optional Number of neighbors in sampling, -1 for all neighbors. Default: ``-1``. alpha : float, optional Weight of the radius loss. Default: ``1``. beta : float, optional Weight of the reconstruction loss. Default: ``1``. gamma : float, optional Weight of the homophily loss. Default: ``1``. warmup : int, optional The number of epochs for warm-up training. Default: ``2``. k : int, optional The number of clusters. Default: ``2``. verbose : int, optional Verbosity mode. Range in [0, 3]. Larger value for printing out more log information. Default: ``0``. save_emb : bool, optional Whether to save the embedding. Default: ``False``. compile_model : bool, optional Whether to compile the model with ``torch_geometric.compile``. Default: ``False``. **kwargs Other parameters for the backbone model. Attributes ---------- decision_score_ : torch.Tensor The outlier scores of the training data. Outliers tend to have higher scores. This value is available once the detector is fitted. threshold_ : float The threshold is based on ``contamination``. It is the :math:`N \\times` ``contamination`` most abnormal samples in ``decision_score_``. The threshold is calculated for generating binary outlier labels. label_ : torch.Tensor The binary labels of the training data. 0 stands for inliers and 1 for outliers. It is generated by applying ``threshold_`` on ``decision_score_``. emb : torch.Tensor or tuple of torch.Tensor or None The learned node hidden embeddings of shape :math:`N \\times` ``hid_dim``. Only available when ``save_emb`` is ``True``. When the detector has not been fitted, ``emb`` is ``None``. When the detector has multiple embeddings, ``emb`` is a tuple of torch.Tensor. """ def __init__(self, hid_dim=64, num_layers=2, dropout=0., weight_decay=0., act=torch.nn.functional.relu, backbone=GCN, contamination=0.1, lr=4e-3, epoch=100, gpu=-1, batch_size=0, num_neigh=-1, alpha=1, beta=1, gamma=1, warmup=2, k=2, verbose=0, save_emb=False, compile_model=False, **kwargs): if num_neigh != 0 and backbone == MLP: warnings.warn('MLP does not use neighbor information.') num_neigh = 0 self.alpha = alpha self.beta = beta self.gamma = gamma self.warmup = warmup self.k = k super(DMGD, self).__init__(hid_dim=hid_dim, num_layers=num_layers, dropout=dropout, weight_decay=weight_decay, act=act, backbone=backbone, contamination=contamination, lr=lr, epoch=epoch, gpu=gpu, batch_size=batch_size, num_neigh=num_neigh, verbose=verbose, save_emb=save_emb, compile_model=compile_model, **kwargs) def process_graph(self, data): DMGDBase.process_graph(data) def init_model(self, **kwargs): if self.save_emb: self.emb = torch.zeros(self.num_nodes, self.hid_dim) return DMGDBase(in_dim=self.in_dim, hid_dim=self.hid_dim, num_layers=self.num_layers, dropout=self.dropout, act=self.act, backbone=self.backbone, alpha=self.alpha, beta=self.beta, gamma=self.gamma, warmup=self.warmup, k=self.k, **kwargs).to(self.device) def forward_model(self, data): batch_size = data.batch_size x = edge_index = x_, nd, emb = self.model(x, edge_index) loss, score = self.model.loss_func(x[:batch_size], x_[:batch_size], nd[:batch_size], emb[:batch_size]) return loss, score.detach().cpu() def decision_function(self, data, label=None): if data is not None: warnings.warn("This detector is transductive only. " "Training from scratch with the input data."), label) return self.decision_score_