Skip to content

Commit bb699cd

Browse files
committed
maxcutpool accepted
1 parent 8d4ad09 commit bb699cd

File tree

9 files changed

+20
-11
lines changed

9 files changed

+20
-11
lines changed

_data/publications.yml

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -34,6 +34,7 @@
3434
3535
- title: "MaxCutPool: differentiable feature-aware Maxcut for pooling in graph neural networks"
3636
authors: "Carlo Abate, Filippo Maria Bianchi"
37+
venue: "ICLR 2025"
3738
figure: "figs/publications/maxcutpool.png"
3839
abstract: "We propose a novel approach to compute the MAXCUT in attributed graphs, i.e., graphs with features associated with nodes and edges. Our approach is robust to the underlying graph topology and is fully differentiable, making it possible to find solutions that jointly optimize the MAXCUT along with other objectives. Based on the obtained MAXCUT partition, we implement a hierarchical graph pooling layer for Graph Neural Networks, which is sparse, differentiable, and particularly suitable for downstream tasks on heterophilic graphs."
3940
github: "https://github.com/NGMLGroup/MaxCutPool"

_news/accepted_maxcut.md

Lines changed: 14 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,14 @@
1+
---
2+
title: "Paper accepted at ICLR"
3+
layout: post
4+
date: 2025-01-23
5+
published: true
6+
---
7+
8+
The paper "*MaxCutPool: differentiable feature-aware Maxcut for pooling in graph neural networks*" by **Carlo Abate** and **Filippo Maria Bianchi** has been accepted at ICLR 2025!
9+
10+
<!--more-->
11+
12+
The paper proposes a novel approach to compute a MaxCut partition in attributed graphs and can be used to implement pooling in Graph Neural Networks. It works particulary well on heterophilic graphs.
13+
14+
The preprint is available on [Arxiv](https://arxiv.org/abs/2409.05100) and the code on [Github](https://github.com/NGMLGroup/MaxCutPool).

_news/pooling_blog.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -5,7 +5,7 @@ date: 2024-12-19
55
published: true
66
---
77

8-
New blog on [Pooling in Graph Neural Networks](https://gnn-pooling.notion.site/)!
8+
A new blog on [Pooling in Graph Neural Networks](https://gnn-pooling.notion.site/) by **Filippo Maria Bianchi** is out!
99

1010
<!--more-->
1111

_news/preprint_bnpool.md

Lines changed: 1 addition & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -5,9 +5,7 @@ date: 2025-01-20
55
published: true
66
---
77

8-
"*BN-Pool: a Bayesian Nonparametric Approach to Graph Pooling*"
9-
10-
By **Daniele Castellana** & **Filippo Maria Bianchi**.
8+
The paper "*BN-Pool: a Bayesian Nonparametric Approach to Graph Pooling*" by **Daniele Castellana** & **Filippo Maria Bianchi** is out!
119

1210
<!--more-->
1311

_news/preprint_koopman_stgnn.md

Lines changed: 1 addition & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -5,9 +5,7 @@ date: 2024-10-15
55
published: true
66
---
77

8-
"*Interpreting Temporal Graph Neural Networks with Koopman Theory*"
9-
10-
By Michele Guerra, Simone Scardapane, and Filippo Maria Bianchi.
8+
The paper "*Interpreting Temporal Graph Neural Networks with Koopman Theory*" by **Michele Guerra**, **Simone Scardapane**, and **Filippo Maria Bianchi** is out!
119

1210
<!--more-->
1311

_news/preprint_maxcut.md

Lines changed: 1 addition & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -5,9 +5,7 @@ date: 2024-09-10
55
published: true
66
---
77

8-
"*MaxCutPool: differentiable feature-aware Maxcut for pooling in graph neural networks*"
9-
10-
By Carlo Abate and Filippo Maria Bianchi.
8+
The paper "*MaxCutPool: differentiable feature-aware Maxcut for pooling in graph neural networks*" by **Carlo Abate** and **Filippo Maria Bianchi** is out!
119

1210
<!--more-->
1311

_news/relay.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -5,7 +5,7 @@ date: 2023-11-01
55
published: true
66
---
77

8-
A new 4-years NFR project has been funded!
8+
A new 4-years NFR project has been funded! The project focuses on relational deep learning for energy analytics.
99

1010
<!--more-->
1111

figs/NGMLGlogo.png

-467 KB
Binary file not shown.

figs/publications/maxcutpool.png

191 KB
Loading

0 commit comments

Comments
 (0)