Steve Azzolin's Avatar

Steve Azzolin

@steveazzolin

ELLIS PhD student @ UNITN/UniCambridge || Prev. Visiting Research Student at UniCambridge || Prev. Research intern at SISLab

202
Followers
127
Following
14
Posts
02.12.2024
Joined
Posts Following

Latest posts by Steve Azzolin @steveazzolin

Beyond Topological Self-Explainable GNNs: A Formal Explainability... Self-Explainable Graph Neural Networks (SE-GNNs) are popular explainable-by-design GNNs, but their explanations' properties and limitations are not well understood. Our first contribution fills...

Paper: openreview.net/forum?id=mkq...

13.07.2025 17:29 πŸ‘ 0 πŸ” 0 πŸ’¬ 0 πŸ“Œ 0

πŸ’‘What can we do to make self-explanations less ambiguous?

-> We propose to automatically adapt explanations to the task by stitching together SE-GNNs with white-box models and combining their explanations.

13.07.2025 17:29 πŸ‘ 0 πŸ” 0 πŸ’¬ 1 πŸ“Œ 0

- Self-explanations can be "unfaithful" by design

13.07.2025 17:29 πŸ‘ 0 πŸ” 0 πŸ’¬ 1 πŸ“Œ 0

- Models encoding different tasks can produce the same self-explanations, limiting the usefulness of explanations

13.07.2025 17:29 πŸ‘ 0 πŸ” 0 πŸ’¬ 1 πŸ“Œ 0

Studying some popular models, we found that:

- The information that self-explanations convey can radically change based on the underlying task to be explained, which is, however, generally unknown

13.07.2025 17:29 πŸ‘ 0 πŸ” 0 πŸ’¬ 1 πŸ“Œ 0
Post image

πŸ€” What are the properties of self-explanations in GNNs? What can we expect from them?

We investigate this in our #ICML25 paper.

Come to have a chat at poster session 5, Thu 17 11 am.

w. Sagar Malhotra @andreapasspr.bsky.social @looselycorrect.bsky.social

13.07.2025 17:29 πŸ‘ 1 πŸ” 0 πŸ’¬ 1 πŸ“Œ 0

Happening tomorrow!

Poster number 508
Saturday's session 10-12:30

25.04.2025 14:27 πŸ‘ 0 πŸ” 1 πŸ’¬ 0 πŸ“Œ 0

3. ITS ROLE IN OOD GENERALISATION

Domain-Invariant GNNs make predictions over a domain-invariant subgraph to achieve OOD generalisation. We show that unless this subgraph is also *sufficient*, DIGNNs are not domain-invariant.

5/5

17.04.2025 13:43 πŸ‘ 0 πŸ” 0 πŸ’¬ 0 πŸ“Œ 0

2. HOW GNNs AIM TO ACHIEVE IT

We highlight several architectural design choices of Self-Explainable GNNs favoring information leakage from nodes outside the explanation, and propose mitigations.

4/5

17.04.2025 13:43 πŸ‘ 0 πŸ” 0 πŸ’¬ 1 πŸ“Œ 0

We propose rethinking faithfulness from three essential angles:

1. HOW TO COMPUTE IT

Many ways to compute faithfulness exists, but we show:

- they are not interchangeable
- some of them do not have the desired semantics

3/5

17.04.2025 13:43 πŸ‘ 0 πŸ” 0 πŸ’¬ 1 πŸ“Œ 0

Paper: "Reconsidering Faithfulness in Regular, Self-Explainable and Domain Invariant GNNs"
Link: openreview.net/forum?id=kiO...
Poster session: 26 April 10am

2/5

17.04.2025 13:43 πŸ‘ 0 πŸ” 0 πŸ’¬ 1 πŸ“Œ 0
Post image

Faithfulness of GNN explanations isn’t one-size-fits-all🧒
Our last @iclr-conf.bsky.social paper breaks it down across:

1. Evaluation metrics
2. Model implementations
3. OOD generalisation

w: Antonio L. @looselycorrect.bsky.social @andreapasserini.bsky.social

1/5

17.04.2025 13:43 πŸ‘ 6 πŸ” 3 πŸ’¬ 1 πŸ“Œ 1

Kudos to the organisers for setting up the poster session in the fanciest room I've ever seenπŸ‘€

08.12.2024 21:26 πŸ‘ 3 πŸ” 0 πŸ’¬ 1 πŸ“Œ 0

Hello World!

02.12.2024 09:45 πŸ‘ 7 πŸ” 0 πŸ’¬ 1 πŸ“Œ 0