Comments (10)
Hi, -r1
means the inverse direction of r1
. For example, if r1
denotes the relation "Interact", -r1 means the relation of "IsInteractedBy". Thanks for your interest.
from knowledge_graph_attention_network.
Thank you for your explanation. In your work, the neighbors of each entity are their target nodes. Then if u1 is the 4-layer neighbor of u2? the information from u1 is encoded in e_u2(4)?
And how the inversed relation is modeled in training process? because you say that your CKG is a directed graph.
from knowledge_graph_attention_network.
I just don't understand the propagation process in CKG from this example.
from knowledge_graph_attention_network.
Another question: for the CF bpr loss function part, is the propagation starts only from the user nodes and item nodes in the user-item interacitons, not all the nodes in CKG are activated in GCN? but in the transR part, all the triples in the CKG are considered?
Have you ever tried also using GCN in the transR part? the h r t embeddings in transR are also generated from the GCN propagation process, then GCN can traverse the whole CKG.
Hope for your comment, thank you.
from knowledge_graph_attention_network.
Hi,
-
CKG is a directed graph, and we model the relations between any two nodes in canonical and inverse directions. Namely, in CKG, there exist
r1
fromu1
toi1
, as well as-r1
fromi1
tou1
. They are two different relations. For more information, please refer to Section 2 and the code. -
As for the example, please refer to the analogous instance in Figure 3 of our NGCF SIGIR19.
-
For the loss of BPR, it provides the supervision signals from the user-item interactions, which are built upon the outputs of the propagation process. For the KGE part, TransR serves more like the regularization term, to regularize the initial representations.
-
Thanks for your insightful suggestions. We actually tried to employ TransR on the GCN-output representations. It would perform slightly better but at the cost of time and model complexity.
from knowledge_graph_attention_network.
Hi, i am curious about the TopK setting. You post the results when K = 20. How about the results when K is smaller like 5 or 10? Thank you.
from knowledge_graph_attention_network.
Hi, we only have done the experiments when K spans from 20, 40, 60, to 80 and 100. You can try smaller K by changing the hyperparameter Ks
(e.g., --Ks [1,2,3,5,10]
). Thanks for your interest.
from knowledge_graph_attention_network.
Hi, for Figure3(b), why the results decrease a lot although the density increase?
from knowledge_graph_attention_network.
Thanks for your comment. We currently work on this phenomenon but have no exact idea of why it happened.
from knowledge_graph_attention_network.
Thank you for your explanation. In your work, the neighbors of each entity are their target nodes. Then if u1 is the 4-layer neighbor of u2? the information from u1 is encoded in e_u2(4)? And how the inversed relation is modeled in training process? because you say that your CKG is a directed graph.
Hi,have you solved your question?
I don't understand the example, too.
from knowledge_graph_attention_network.
Related Issues (20)
- I have a question about kg_final.txt HOT 1
- I have a question about memory growth HOT 1
- ERROR: loss@phase2 is nan HOT 1
- Yelp dataset is missing HOT 2
- Problem of reproducing baseline model
- Question about data partition: did you use validation data for selecting best models?
- 卡在epoch0
- 采用TransR方法训练实体表示的作用? HOT 1
- 关于RippleNet 的ratings_final.txt生成问题 HOT 1
- how to make kg_final.txt HOT 3
- IndexError: too many indices for array
- How to get the embeddings(mf.npz) under the pretrain folder?
- UnicodeDecodeError HOT 1
- how to print the attention score with tensorflow?
- how to calculate the %improv?
- Item_list.txt is missing spaces in the yelp2018
- Which epoch should I use when I use bprmf to generate embedding in pretrain?
- about without pretraining
- Performance on yelp2018 with KGAT
- Clarification Needed on kg_final.txt Data Contents HOT 1
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 knowledge_graph_attention_network.