Gunnar König

Not that I know of. But the method is relatively easy to implement. Please reach out if you would like to use it. I'm happy to assist!

Sounds interesting? Have a look at our paper!

Joint work with Eric Günther and @ulrikeluxburg.bsky.social.

GitHub - gcskoenig/dipd: Code implementing the DIP Decomposition that disentangles standalone contributions and cooperative contributions stemming from interactions and dependencies in global loss-bas... Code implementing the DIP Decomposition that disentangles standalone contributions and cooperative contributions stemming from interactions and dependencies in global loss-based feature attribution...

DIP is
✅ unique under mild assumptions,
✅ easy to interpret,
✅ entails an efficient estimation procedure,
✅ describes properties of the data (instead of just a specific model), and
✅ comes with a python implementation (github.com/gcskoenig/dipd).

In our recent AISTATS paper, we propose DIP, a novel mathematical decomposition of feature attribution scores that cleanly separates individual feature contributions and the contributions of interactions and dependencies.

Dependencies are not only a neglected cooperative force but also complicate the definition and quantification of feature interactions. In particular, the contributions of interactions and dependencies may cancel each other out and must be disentangled to be fully revealed.

For example, suppose we predict kidney function (Y) from creatinine (C) and muscle mass (M), and that C reflects Y but also M, which is not linked to Y. Here, M becomes useful once combined with C, as it allows us to subtract irrelevant variation from C. In other words, C&M cooperate via dependence!

Determining whether variables are relevant due to cooperation is crucial, as variables that cooperate must be considered jointly to understand their relevance. Notably, features cooperate not only through interactions but also through statistical dependencies, which existing methods neglect.

In many XAI applications, it is crucial to determine whether features contribute individually or only when combined. However, existing methods fail to reveal cooperations since they entangle individual contributions with those made via interactions and dependencies. We show how to disentangle them!

Feature importance measures can clarify or mislead. PFI, LOCO, and SAGE each answer a different question.
Understand how to pick the right tool and avoid spurious conclusions: mcml.ai/news/2025-03...
@fionaewald.bsky.social @ludwig-bothmann.bsky.social @giuseppe88.bsky.social @gunnark.bsky.social

Finally made it to bluesky as well ...

And the video of Gunnar's talk is up on YouTube in case you missed it: youtu.be/7MrMjabTbuM

@gunnark.bsky.social

I recall you had an iPad -- why did you switch?

A starter pack of people working on interpretability / explainability of all kinds, using theoretical and/or empirical approaches.

Reply or DM if you want to be added, and help me reach others!

go.bsky.app/DZv6TSS

Tübingen AI Join the conversation

Here's a fledgling starter pack for the AI community in Tübingen. Let me know if you'd like to be added!

go.bsky.app/NFbVzrA