dmlc--dgl
ziqiaomeng
ddeb86f91c
* Prepare for metapath sampler This file is just for reviewing metapath sampling algorithm (Python version). * Delete metapath_sampler * Prepare for metapath sampler This file is just for reviewing metapath sampling algorithm (Python code). * Add files via upload * Create metapath2vec.md * Add files via upload * Delete data_handler.py * Delete word2vec.py * Delete word_train.py * Add files via upload Metapath2vec implementations. Metapath2vec++ needs negative sampler optimization. * Delete shuffle_training.py * Delete test.py * Add files via upload * Delete sampler.py * Delete metapath_sampler.md * Add files via upload * Update and rename shuffle_training.py to metapath2vec.py * Update reading_data.py * Update metapath2vec.md * Update metapath2vec.md * Update metapath2vec.md * Update metapath2vec.md * Update metapath2vec.md * Create label 2 * Delete label 2 * Create testing.md * Add files via upload * Create sample.md * Add files via upload * Delete sampler.py * Add files via upload * Delete googlescholar.8area.author.label.txt * Delete googlescholar.8area.venue.label.txt * Delete testing.md * Delete id_author.txt * Delete id_conf.txt * Delete paper.txt * Delete paper_author.txt * Delete paper_conf.txt * Delete sample.md * Delete sampler.py * Add files via upload * Add files via upload * Add files via upload * Delete reading_data.py * Add files via upload * Add files via upload * Delete metapath2vec.py * Add files via upload * Rename shuffle_training.py to metapath2vec.py * Update metapath2vec.md * Delete reading_data.py * add comments and remov e commented codes
46 行
1.6 KiB
Python
46 行
1.6 KiB
Python
import torch
|
|
import torch.nn as nn
|
|
import torch.nn.functional as F
|
|
from torch.nn import init
|
|
|
|
"""
|
|
u_embedding: Embedding for center word.
|
|
v_embedding: Embedding for neighbor words.
|
|
"""
|
|
|
|
|
|
class SkipGramModel(nn.Module):
|
|
|
|
def __init__(self, emb_size, emb_dimension):
|
|
super(SkipGramModel, self).__init__()
|
|
self.emb_size = emb_size
|
|
self.emb_dimension = emb_dimension
|
|
self.u_embeddings = nn.Embedding(emb_size, emb_dimension, sparse=True)
|
|
self.v_embeddings = nn.Embedding(emb_size, emb_dimension, sparse=True)
|
|
|
|
initrange = 1.0 / self.emb_dimension
|
|
init.uniform_(self.u_embeddings.weight.data, -initrange, initrange)
|
|
init.constant_(self.v_embeddings.weight.data, 0)
|
|
|
|
def forward(self, pos_u, pos_v, neg_v):
|
|
emb_u = self.u_embeddings(pos_u)
|
|
emb_v = self.v_embeddings(pos_v)
|
|
emb_neg_v = self.v_embeddings(neg_v)
|
|
|
|
score = torch.sum(torch.mul(emb_u, emb_v), dim=1)
|
|
score = torch.clamp(score, max=10, min=-10)
|
|
score = -F.logsigmoid(score)
|
|
|
|
neg_score = torch.bmm(emb_neg_v, emb_u.unsqueeze(2)).squeeze()
|
|
neg_score = torch.clamp(neg_score, max=10, min=-10)
|
|
neg_score = -torch.sum(F.logsigmoid(-neg_score), dim=1)
|
|
|
|
return torch.mean(score + neg_score)
|
|
|
|
def save_embedding(self, id2word, file_name):
|
|
embedding = self.u_embeddings.weight.cpu().data.numpy()
|
|
with open(file_name, 'w') as f:
|
|
f.write('%d %d\n' % (len(id2word), self.emb_dimension))
|
|
for wid, w in id2word.items():
|
|
e = ' '.join(map(lambda x: str(x), embedding[wid]))
|
|
f.write('%s %s\n' % (w, e)) |