Skip to content

Commit

Permalink
update images
Browse files Browse the repository at this point in the history
  • Loading branch information
DavidZWZ committed Jul 22, 2024
1 parent dd24b9f commit 23bc52a
Showing 1 changed file with 5 additions and 3 deletions.
8 changes: 5 additions & 3 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -5,12 +5,14 @@ Pytorch Implementation for CIKM 2024 Full Research Track Paper:
> 33rd ACM International Conference on Information and Knowledge , CIKM 2024 <br>
> Weizhi Zhang, Liangwei Yang, Zihe Song, Henry Peng Zou, Ke Xu, Liancheng Fang, Philip S. Yu <br>
## Investigation: Do We Really Need Graph Convolution During Training?
<p align="center">
<img src="Images/Prelim.png" alt="Investigation of Role of Graph Convolution" width="33%">
<img src="Images/BFS-DFS.png" alt="BFS (GCN) vs DFS (MF) perspective" width="33%"/>
<img src="Images/Trade-off.png" alt="The Embedding Discrepancy Issue" width="33%"/>
<img src="Images/Prelim.png" alt="Investigation of Role of Graph Convolution" width="300">
<img src="Images/BFS-DFS.png" alt="BFS (GCN) vs DFS (MF) perspective" width="300"/>
<img src="Images/Trade-off.png" alt="The Embedding Discrepancy Issue" width="300"/>
</p>

## Proposed Solution: Light Post-Training Graph-ODE for Efficient Recommendation.
![Framework](Images/Framework.png)

## Set up:
Expand Down

0 comments on commit 23bc52a

Please sign in to comment.