Paper: openreview.net/forum?id=mkq...
π‘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.
- Self-explanations can be "unfaithful" by design
- Models encoding different tasks can produce the same self-explanations, limiting the usefulness of explanations
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
π€ 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
Happening tomorrow!
Poster number 508
Saturday's session 10-12:30
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
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
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
Paper: "Reconsidering Faithfulness in Regular, Self-Explainable and Domain Invariant GNNs"
Link: openreview.net/forum?id=kiO...
Poster session: 26 April 10am
2/5
Faithfulness of GNN explanations isnβt one-size-fits-allπ§’
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
Kudos to the organisers for setting up the poster session in the fanciest room I've ever seenπ
Hello World!