-
Notifications
You must be signed in to change notification settings - Fork 0
/
my_config.yml
95 lines (86 loc) · 3.16 KB
/
my_config.yml
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
###########################################################
# Node embedding configuration file
###########################################################
application:
graph
resource:
# List of GPU ids. Default is all GPUs
gpus: []
# Memory limit for each GPU in bytes. Default is all available memory.
gpu_memory_limit: auto
# Number of CPU thread per GPU. Default is all CPUs.
cpu_per_gpu: auto
# Dimension of the embeddings.
dim: 32
format:
# String of delimiter characters. Change it if your node name contains blank character.
delimiters: " \t\r\n"
# Prefix of comment strings. Change it if you use comment style other than Python.
comment: "#"
graph:
# Path to edge list file. Each line should be one of the following
# [node 1] [delimiter] [node 2] [comment]...
# [node 1] [delimiter] [node 2] [delimiter] [weight] [comment]...
# [comment]...
# For standard datasets, you can specify them by <[dataset].[split]>.
file_name: "data/full.txt"
# Symmetrize the graph or not. True is recommended.
as_undirected: true
# Normalize the adjacency matrix or not. This may influence the performance a little.
normalization: false
build:
optimizer:
# Optimizer.
type: SGD
# Learning rate. Default is usually reasonable.
lr: 0.025
# Weight decay.
weight_decay: 0.005
# Learning rate schedule, can be "linear" or "constant". Linear is recommended.
schedule: linear
# Number of partitions. Auto is recommended.
num_partition: auto
# Number of negative samples per positive sample.
# Larger value results in slower training.
# The performance may be influenced by num_negative * negative_weight.
num_negative: 1
# Batch size of samples in CPU-GPU transfer. Default is recommended.
batch_size: 100000
# Number of batches in a partition block.
# Default is recommended.
episode_size: auto
# # Comment out this section if not needed.
# load:
# # Path to model file, can be "*.pkl".
# file_name: graph.pkl
train:
# Model, can be DeepWalk, LINE or node2vec.
model: LINE
# Number of epochs. Default is usually reasonable for sparse graphs.
# For dense graphs (|E| / |V| > 100), you may use smaller values.
num_epoch: 2000
# Augmentation step. Default is usually reasonable.
# Larger value is needed for sparser graphs.
augmentation_step: 5
# Length of each random walk. Default is recommended.
random_walk_length: 40
# Batch size of random walks in samplers. Default is recommended.
random_walk_batch_size: 100
# Log every n batches.
log_frequency: 3000
# Comment out this section if not needed.
# evaluate:
# - task: link prediction
# # Path to link prediction file. Each line should be
# # [node 1] [delimiter] [node 2] [delimiter] [label]
# # where label is 1 for positive and 0 for negative.
# file_name: data/test2.txt
# # Path to filter file. If you aren't sure that training data is excluded in evaluation,
# # you can specify the training edge list here.
# filter_file:
# Comment out this section if not needed.
save:
# Path to save file, can be "*.pkl".
file_name: embedding/dim32-len40/line_full.pkl
# Save hyperparameters or not.
save_hyperparameter: true