Comments (5)
Thank you for pointing out. There's a weight parameter missing in the paper published on arXiv. In our implementation, there should be a weight matrix following the adjacency matrix multiplied with the list of item vectors (Equation 1). We have corrected this problem in the final version and will update the paper when the final conference proceeding is available.
from sr-gnn.
I have two questions for the paper.
- In equation (6), is m the number of items in a session or in the whole dataset?
- Is the Vi in equation (6) the same as the Vi in equation (8)? The one in (6) seems to be put into (1) ~ (5), but the one in (8) is not.
from sr-gnn.
I have two questions for the paper.
- In equation (6), is m the number of items in a session or in the whole dataset?
- Is the Vi in equation (6) the same as the Vi in equation (8)? The one in (6) seems to be put into (1) ~ (5), but the one in (8) is not.
Thank you for your interest in our paper.
A1: m refers to the number of all unique items.
A2: Vector
from sr-gnn.
I have two questions for the paper.
- In equation (6), is m the number of items in a session or in the whole dataset?
- Is the Vi in equation (6) the same as the Vi in equation (8)? The one in (6) seems to be put into (1) ~ (5), but the one in (8) is not.
Thank you for your interest in our paper.
A1: m refers to the number of all unique items.
A2: Vector$\mathbf{v}_i$ in bold denotes the embedding of item$v_i$ .
Thank you for your reply, but I still feel confused about this.
If the m in equation (6) is the number of all unique items in the whole dataset, the size of alpha in line 84 of pytorch_code/model.py should be batch_size * number_all_unique_items * 1, but it is batch_size * seq_length * 1 when I run the code.
from sr-gnn.
I have two questions for the paper.
- In equation (6), is m the number of items in a session or in the whole dataset?
- Is the Vi in equation (6) the same as the Vi in equation (8)? The one in (6) seems to be put into (1) ~ (5), but the one in (8) is not.
Thank you for your interest in our paper.
A1: m refers to the number of all unique items.
A2: Vector$\mathbf{v}_i$ in bold denotes the embedding of item$v_i$ .Thank you for your reply, but I still feel confused about this.
If the m in equation (6) is the number of all unique items in the whole dataset, the size of alpha in line 84 of pytorch_code/model.py should be batch_size * number_all_unique_items * 1, but it is batch_size * seq_length * 1 when I run the code.
Our mistake. Thanks for pointing our. It should be summing over all items within one session, so the m in Eq. (6) should be changed to n.
from sr-gnn.
Related Issues (20)
- Why should choose a relatively small number of training steps in BPTT? HOT 1
- 数据处理问题 HOT 1
- 数据集统计问题 HOT 1
- Tensorflow and PyTorch code have different performance HOT 4
- preprocess.py doesn't work on yoochoose-clicks.dat HOT 1
- The difference in 5 equation in paper and code HOT 3
- Inconsistent performance of POP HOT 1
- GGNN function in tensorflow code
- can you share data please ? HOT 4
- GPU
- GPU使用率低怎么破
- could run with tf-gpu==1.14?
- about the connection matrix HOT 1
- 'GAT' in tensorlfow code HOT 1
- 关于在Diginegica数据集上的实验结果 HOT 7
- DIGINETICA数据集下载不了 HOT 1
- 关于GNN实现部分的一个部分
- The source of small dataset 'sample' HOT 1
- Why not using the first embedding of nn.Embedding ? HOT 1
- 论文示意图与代码不符? HOT 7
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 sr-gnn.