def __init__(self, args, logger):
super(GraphSAGE, self).__init__(args, logger)
self.adj = utils.build_adj(self.graph, self.num_node)
edge_dist_dict, node_dist_dict = utils.makeDist(
args.link_file, args.negative_power)
self.edges_alias_sampler = utils.VoseAlias(edge_dist_dict)
self.nodes_alias_sampler = utils.VoseAlias(node_dist_dict)
self.taxo_parent2children, self.taxo_child2parents, self.nodeid2category, self.category2nodeid, self.category2id, self.nodeid2path \
= utils.read_taxos(args.taxo_file, args.taxo_assign_file, args.extend_label)
self.root_nodes = [
i for i in self.root_nodes if i in self.nodeid2category
]
edgedistdict, taxodistdict = self.make_dist()
self.taxo_edge_alias_sampler = utils.VoseAlias(edgedistdict)
self.taxo_alias_sampler = utils.VoseAlias(taxodistdict)
self.num_category = len(self.category2id)
self.taxo_rootid = self.category2id['root']
self.print(f"num of category: {self.num_category}")
if args.rand_init:
taxo_init_embed = utils.init_embed(self.num_category,
self.embed_dim)
else:
taxo_init_embed = self.init_taxo_embed(self.pre_train_embedding)
self.model = TaxoGCNModel(self.pre_train_embedding, taxo_init_embed,
args.dropout)
self.model.to(args.device)
def __init__(self, args, logger=None):
super(TaxoGAN_V3, self).__init__(args, logger)
self.taxo_parent2children, self.taxo_child2parents, self.nodeid2category, self.category2nodeid, self.category2id, self.nodeid2path \
= utils.read_taxos(args.taxo_file, args.taxo_assign_file)
self.root_nodes = [
i for i in self.root_nodes if i in self.nodeid2category
]
self.num_category = len(self.category2id)
self.taxo_rootid = self.category2id['root']
self.print(f"num of category: {self.num_category}")
if args.rand_init:
taxo_init_embed = utils.init_embed(self.num_category,
self.embed_dim)
else:
taxo_init_embed = self.init_taxo_embed(self.pre_train_embedding)
# build the model
self.generator = Generator_V3(args.lambda_g, self.pre_train_embedding,
taxo_init_embed, args.lambda_taxo,
self.num_category, args.transform)
self.discriminator = Discriminator_V3(
args.lambda_d, self.pre_train_embedding, taxo_init_embed,
args.lambda_taxo, self.num_category, args.transform)
self.generator.to(args.device)
self.discriminator.to(args.device)
self.taxo_all_score = None
def __init__(self, args, logger):
super(PTE, self).__init__(args, logger)
edge_dist_dict, node_dist_dict = utils.makeDist(
args.link_file, args.negative_power)
self.edges_alias_sampler = utils.VoseAlias(edge_dist_dict)
self.nodes_alias_sampler = utils.VoseAlias(node_dist_dict)
self.taxo_parent2children, self.taxo_child2parents, self.nodeid2category, self.category2nodeid, self.category2id, self.nodeid2path \
= utils.read_taxos(args.taxo_file, args.taxo_assign_file, args.extend_label)
edgedistdict, taxodistdict = self.make_dist()
self.taxo_edge_alias_sampler = utils.VoseAlias(edgedistdict)
self.taxo_alias_sampler = utils.VoseAlias(taxodistdict)
self.num_category = len(self.category2id)
self.taxo_rootid = self.category2id['root']
self.category2level = utils.category2level(range(self.num_category),
self.taxo_child2parents)
level2category = defaultdict(list)
for cate, level in self.category2level.items():
level2category[level].append(cate)
self.level2category = dict(level2category)
self.print(f"num of category: {self.num_category}")
if args.rand_init:
taxo_init_embed = utils.init_embed(self.num_category,
self.embed_dim)
else:
taxo_init_embed = self.init_taxo_embed(self.pre_train_embedding)
self.model = TaxoSkipGramModel(self.pre_train_embedding,
taxo_init_embed)
self.model.to(args.device)
def __init__(self, args, logger=None):
super(TaxoGAN_V1, self).__init__(args, logger)
self.taxo_parent2children, self.taxo_child2parents, self.nodeid2category, self.category2nodeid, self.category2id, self.nodeid2path \
= utils.read_taxos(args.taxo_file, args.taxo_assign_file)
self.root_nodes = [
i for i in self.root_nodes if i in self.nodeid2category
]
categories = list(self.category2nodeid.keys())
self.nodeid2neg_category = {
node:
[i for i in categories if i not in self.nodeid2category[node]]
for node in self.root_nodes
}
edgedistdict, taxodistdict = self.make_dist()
self.taxo_edge_alias_sampler = utils.VoseAlias(edgedistdict)
self.taxo_alias_sampler = utils.VoseAlias(taxodistdict)
self.num_category = len(self.category2id)
self.taxo_rootid = self.category2id['root']
self.category2level = utils.category2level(range(self.num_category),
self.taxo_child2parents)
self.print(f"num of category: {self.num_category}")
if args.rand_init:
taxo_init_embed = utils.init_embed(self.num_category,
self.embed_dim)
else:
taxo_init_embed = self.init_taxo_embed(self.pre_train_embedding)
max_level = 0
for _, paths in self.nodeid2path.items():
for p in paths:
max_level = max(max_level, len(p))
self.max_level = max_level
# build the model
self.generator = Generator(args.lambda_g, self.pre_train_embedding,
taxo_init_embed, args.lambda_taxo,
max_level + 1, args.transform)
self.discriminator = Discriminator(args.lambda_d,
self.pre_train_embedding,
taxo_init_embed, args.lambda_taxo,
max_level + 1, args.transform)
self.generator.to(args.device)
self.discriminator.to(args.device)
def __init__(self, args, logger=None):
super(TaxoGAN_V2, self).__init__(args, logger)
self.taxo_parent2children, self.taxo_child2parents, self.nodeid2category, self.category2nodeid, self.category2id, self.nodeid2path \
= utils.read_taxos(args.taxo_file, args.taxo_assign_file)
self.root_nodes = [
i for i in self.root_nodes if i in self.nodeid2category
]
self.num_category = len(self.category2id)
self.taxo_rootid = self.category2id['root']
self.category2level = utils.category2level(range(self.num_category),
self.taxo_child2parents)
self.levels = [
self.category2level[i] for i in range(self.num_category)
]
self.level2category = collections.defaultdict(list)
self.max_level = max(self.levels)
for i, level in enumerate(self.levels):
self.level2category[level].append(i)
self.print(f"num of category: {self.num_category}")
if args.rand_init:
taxo_init_embed = utils.init_embed(self.num_category,
self.embed_dim)
else:
taxo_init_embed = self.init_taxo_embed(self.pre_train_embedding)
# build the model
self.generator = Generator_V2(args.lambda_g, self.pre_train_embedding,
taxo_init_embed, args.lambda_taxo,
self.max_level + 1, args.transform)
self.discriminator = Discriminator_V2(
args.lambda_d, self.pre_train_embedding, taxo_init_embed,
args.lambda_taxo, self.max_level + 1, args.transform)
self.generator.to(args.device)
self.discriminator.to(args.device)
self.taxo_all_score = None
def __init__(self, args, logger=None):
"""initialize the parameters, prepare the data and build the network"""
self.print = logger.info if logger else print
self.device = args.device
self.print(f"Reading data from {args.data_dir}")
self.root_nodes, self.graph, num_link = utils.read_graph(
args.link_file)
self.pre_train_embedding, self.id2name, self.name2id = utils.read_nodes(
args.node_file)
self.num_node = len(self.id2name)
self.embed_dim = args.embed_dim
self.print(f"num of link: {num_link}")
self.print(f"num of node: {self.num_node}")
if args.rand_init or not self.pre_train_embedding:
self.print("randomly initialize node embedding!")
self.embed_dim = args.embed_dim
self.pre_train_embedding = utils.init_embed(
self.num_node, self.embed_dim)
if 'taxonomy' in args.task:
self.taxo_parent2children, self.taxo_child2parents, _, self.category2nodeid, self.category2id, _ \
= utils.read_taxos(args.taxo_file, args.taxo_assign_file, args.extend_label)
self.taxo_rootid = self.category2id['root']
self.task_stats = {
task: {
'best_acc': -1,
'acc': []
}
for task in args.task.split('|')
}
self.stats = {'graph_loss': [], 'taxo_loss': []}
self.model = None