Skip to yearly menu bar Skip to main content


Poster

Incorporating probabilistic domain knowledge into deep multiple instance learning

Ghadi S. Al Hajj · Aliaksandr Hubin · Chakravarthi Kanduri · Milena Pavlović · Knut Rand · Michael Widrich · Anne Solberg · Victor Greiff · Johan Pensar · Günter Klambauer · Geir Kjetil Sandve

Hall C 4-9 #402
[ ] [ Project Page ] [ Paper PDF ]
[ Poster
Tue 23 Jul 4:30 a.m. PDT — 6 a.m. PDT

Abstract:

Deep learning methods, including deep multiple instance learning methods, have been criticized for their limited ability to incorporate domain knowledge. A reason that knowledge incorporation is challenging in deep learning is that the models usually lack a mapping between their model components and the entities of the domain, making it a non-trivial task to incorporate probabilistic prior information. In this work, we show that such a mapping between domain entities and model components can be defined for a multiple instance learning setting and propose a framework DeeMILIP that encompasses multiple strategies to exploit this mapping for prior knowledge incorporation. We motivate and formalize these strategies from a probabilistic perspective. Experiments on an immune-based diagnostics case show that our proposed strategies allow to learn generalizable models even in settings with weak signals, limited dataset size, and limited compute.

Chat is not available.