Comments (3)
你好,我们在 General - ML-1M 里列出了全部的调参范围和最优参数。如果你希望复现最优结果,可以直接将此页面的 properties 和最优参数拼成一个新的 .yaml
,以 SGL 举例:
# dataset config
field_separator: "\t"
seq_separator: " "
USER_ID_FIELD: user_id
ITEM_ID_FIELD: item_id
RATING_FIELD: rating
NEG_PREFIX: neg_
LABEL_FIELD: label
load_col:
inter: [user_id, item_id, rating]
val_interval:
rating: "[3,inf)"
unused_col:
inter: [rating]
# training and evaluation
epochs: 500
train_batch_size: 4096
valid_metric: MRR@10
eval_batch_size: 4096000
# best Hyper-parameter for SGL
learning_rate: 0.002
n_layers: 3
reg_weight: 0.0001
ssl_tau: 0.5
drop_ratio: 0.1
ssl_weight: 0.005
假设此文件名为 sgl_best.yaml
,则可以将其放在根目录,并输下述命令运行
python run_recbole_gnn.py -m SGL -d ml-1m --config_files=sgl_best.yaml
from recbole-gnn.
非常感谢!我还有一个疑问,我在Amazon Book上的实验提示了显存溢出的错误(使用2060显卡,6G显存),您知道这个问题应该如何解决吗?
from recbole-gnn.
Book 数据集上好像确实是需要较大的显存的。
from recbole-gnn.
Related Issues (20)
- [🐛BUG] SRGNN, GCSAN, NISER中的gnn消息聚合似乎没有使用边权重? HOT 2
- 请问General Recommendation的边是否能设置权重? HOT 3
- 如何指定自己的数据集 HOT 1
- [🐛BUG] MHCN在Douban数据集上并没有复现出原论文的效果 HOT 8
- 执行超参数搜索时KeyError报错 HOT 6
- Question: About LightGCN eval mode. HOT 2
- Question: batch of training HOT 4
- [🐛BUG] Recole -GNN error HOT 5
- [🐛BUG] SGL emb_loss should not be averaged. HOT 1
- 关于不同数据集下超参数搜索 HOT 1
- 复现最佳超参问题 HOT 1
- [❓Question] 请问为什么 `sequential_base.yaml` 中 `train_neg_sample_args` 要设置为 `None`? HOT 2
- New dataset not being detected. Where to save the atomic files? HOT 2
- 关于性能的建议
- 关于数据集的问题 HOT 6
- `model_name` [xxx] is not the name of an existing model. HOT 1
- [🐛BUG] 有个空指针异常能帮忙看看吗? HOT 1
- 运行srgnn时报错 HOT 2
- 关于运行SRGNN在douban和yoochoose数据下评价指标为0
- 当我导入yaml文件,报错会反馈无法使用
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from recbole-gnn.