class Net(nn.Module):
def __init__(self, args, dev_id):
super(Net, self).__init__()
self._act = get_activation(args.model_activation)
self.encoder = GCMCLayer(args.rating_vals,
args.src_in_units,
args.dst_in_units,
args.gcn_agg_units,
args.gcn_out_units,
args.gcn_dropout,
args.gcn_agg_accum,
agg_act=self._act,
share_user_item_param=args.share_param,
device=dev_id)
if args.mix_cpu_gpu and args.use_one_hot_fea:
# if use_one_hot_fea, user and movie feature is None
# W can be extremely large, with mix_cpu_gpu W should be stored in CPU
self.encoder.partial_to(dev_id)
else:
self.encoder.to(dev_id)
self.decoder = BiDecoder(in_units=args.gcn_out_units,
num_classes=len(args.rating_vals),
num_basis=args.gen_r_num_basis_func)
self.decoder.to(dev_id)
def forward(self, compact_g, frontier, ufeat, ifeat,
possible_rating_values):
user_out, movie_out = self.encoder(frontier, ufeat, ifeat)
pred_ratings = self.decoder(compact_g, user_out, movie_out)
return pred_ratings
def __init__(self, args):
super(Net, self).__init__()
self._act = get_activation(args.model_activation)
self.encoder = nn.ModuleList()
self.encoder.append(
GCMCLayer(args.rating_vals,
args.src_in_units,
args.dst_in_units,
args.gcn_agg_units,
args.gcn_out_units,
args.gcn_dropout,
args.gcn_agg_accum,
agg_act=self._act,
share_user_item_param=args.share_param,
device=args.device))
self.gcn_agg_accum = args.gcn_agg_accum
self.rating_vals = args.rating_vals
self.device = args.device
self.gcn_agg_units = args.gcn_agg_units
self.src_in_units = args.src_in_units
for i in range(1, args.layers):
if args.gcn_agg_accum == 'stack':
gcn_out_units = args.gcn_out_units * len(args.rating_vals)
else:
gcn_out_units = args.gcn_out_units
self.encoder.append(
GCMCLayer(args.rating_vals,
args.gcn_out_units,
args.gcn_out_units,
gcn_out_units,
args.gcn_out_units,
args.gcn_dropout - i * 0.1,
args.gcn_agg_accum,
agg_act=self._act,
share_user_item_param=args.share_param,
ini=False,
device=args.device))
if args.decoder == "Bi":
self.decoder = BiDecoder(
in_units=args.gcn_out_units, #* args.layers,
num_classes=len(args.rating_vals),
num_basis=args.gen_r_num_basis_func)
'''
self.decoder2 = MLPDecoder(in_units= args.gcn_out_units * 2,
num_classes=len(args.rating_vals),
num_basis=args.gen_r_num_basis_func)
'''
elif args.decoder == "MLP":
if args.loss_func == "CE":
num_classes = len(args.rating_vals)
else:
num_classes = 1
self.decoder = MLPDecoder(in_units=args.gcn_out_units *
args.layers,
num_classes=num_classes,
num_basis=args.gen_r_num_basis_func)
self.rating_vals = args.rating_vals
def __init__(self, args, dev_id):
super(Net, self).__init__()
self._act = get_activation(args.model_activation)
self.encoder = nn.ModuleList()
self.encoder.append(
GCMCLayer(args.rating_vals,
args.src_in_units,
args.dst_in_units,
args.gcn_agg_units,
args.gcn_out_units,
args.gcn_dropout,
args.gcn_agg_accum,
agg_act=self._act,
share_user_item_param=args.share_param,
device=dev_id))
self.rating_vals = args.rating_vals
self.gcn_agg_accum = args.gcn_agg_accum
self.rating_vals = args.rating_vals
self.device = dev_id
self.gcn_agg_units = args.gcn_agg_units
self.src_in_units = args.src_in_units
self.batch_size = args.minibatch_size
for i in range(1, args.layers):
if args.gcn_agg_accum == 'stack':
gcn_out_units = args.gcn_out_units * len(args.rating_vals)
else:
gcn_out_units = args.gcn_out_units
self.encoder.append(
GCMCLayer(args.rating_vals,
args.gcn_out_units,
args.gcn_out_units,
gcn_out_units,
args.gcn_out_units,
args.gcn_dropout - i * 0.1,
args.gcn_agg_accum,
agg_act=self._act,
share_user_item_param=args.share_param,
ini=False,
device=dev_id))
if args.mix_cpu_gpu and args.use_one_hot_fea:
# if use_one_hot_fea, user and movie feature is None
# W can be extremely large, with mix_cpu_gpu W should be stored in CPU
self.encoder.partial_to(dev_id)
else:
self.encoder.to(dev_id)
self.decoder = BiDecoder(in_units=args.gcn_out_units,
num_classes=len(args.rating_vals),
num_basis=args.gen_r_num_basis_func)
self.decoder.to(dev_id)
class Net(nn.Module):
def __init__(self, args, dev_id):
super(Net, self).__init__()
self._act = get_activation(args.model_activation)
self.encoder = GCMCLayer(args.rating_vals,
args.src_in_units,
args.dst_in_units,
args.gcn_agg_units,
args.gcn_out_units,
args.gcn_dropout,
args.gcn_agg_accum,
agg_act=self._act,
share_user_item_param=args.share_param,
device=dev_id)
if args.mix_cpu_gpu and args.use_one_hot_fea:
# if use_one_hot_fea, user and movie feature is None
# W can be extremely large, with mix_cpu_gpu W should be stored in CPU
self.encoder.partial_to(dev_id)
else:
self.encoder.to(dev_id)
self.decoder = DenseBiDecoder(in_units=args.gcn_out_units,
num_classes=len(args.rating_vals),
num_basis=args.gen_r_num_basis_func)
self.decoder.to(dev_id)
def forward(self, compact_g, frontier, ufeat, ifeat,
possible_rating_values):
user_out, movie_out = self.encoder(frontier, ufeat, ifeat)
head_emb = []
tail_emb = []
for possible_rating_value in possible_rating_values:
head, tail = compact_g.all_edges(etype=str(possible_rating_value))
head_emb.append(user_out[head])
tail_emb.append(movie_out[tail])
head_emb = th.cat(head_emb, dim=0)
tail_emb = th.cat(tail_emb, dim=0)
pred_ratings = self.decoder(head_emb, tail_emb)
return pred_ratings
def __init__(self, args, dev_id):
super(Net, self).__init__()
self._act = get_activation(args.model_activation)
self.encoder = GCMCLayer(args.rating_vals,
args.src_in_units,
args.dst_in_units,
args.gcn_agg_units,
args.gcn_out_units,
args.gcn_dropout,
args.gcn_agg_accum,
agg_act=self._act,
share_user_item_param=args.share_param,
device=dev_id)
if args.mix_cpu_gpu and args.use_one_hot_fea:
# if use_one_hot_fea, user and movie feature is None
# W can be extremely large, with mix_cpu_gpu W should be stored in CPU
self.encoder.partial_to(dev_id)
else:
self.encoder.to(dev_id)
self.decoder = BiDecoder(in_units=args.gcn_out_units,
num_classes=len(args.rating_vals),
num_basis=args.gen_r_num_basis_func)
self.decoder.to(dev_id)
def __init__(self, args):
super(Net, self).__init__()
self._act = get_activation(args.model_activation)
self.encoder = GCMCLayer(args.rating_vals,
args.src_in_units,
args.dst_in_units,
args.gcn_agg_units,
args.gcn_out_units,
args.gcn_dropout,
args.gcn_agg_accum,
agg_act=self._act,
share_user_item_param=args.share_param)
self.decoder = BiDecoder(args.rating_vals,
in_units=args.gcn_out_units,
num_basis_functions=args.gen_r_num_basis_func)
def __init__(self, args, **kwargs):
super(Net, self).__init__(**kwargs)
self._act = get_activation(args.model_activation)
with self.name_scope():
self.encoder = GCMCLayer(src_key=args.src_key,
dst_key=args.dst_key,
src_in_units=args.src_in_units,
dst_in_units=args.dst_in_units,
agg_units=args.gcn_agg_units,
out_units=args.gcn_out_units,
num_links=args.nratings,
dropout_rate=args.gcn_dropout,
agg_accum=args.gcn_agg_accum,
agg_act=args.model_activation,
prefix='enc_')
if args.gen_r_use_classification:
self.gen_ratings = BiDecoder(
in_units=args.gcn_out_units,
out_units=args.nratings,
num_basis_functions=args.gen_r_num_basis_func,
prefix='gen_rating')
else:
self.gen_ratings = InnerProductLayer(prefix='gen_rating')
