Neurosymbolic Decision Trees
This work addresses a gap in neurosymbolic AI for researchers and practitioners by enabling structure learning, though it appears incremental as it extends existing decision tree and DeepProbLog methods.
The paper tackles the problem of learning the symbolic structure in neurosymbolic AI, which has been less explored, by introducing neurosymbolic decision trees (NDTs) and a novel algorithm NeuID3, resulting in a model that supports both symbolic and subsymbolic data and exploits background knowledge during tree induction.
Neurosymbolic (NeSy) AI studies the integration of neural networks (NNs) and symbolic reasoning based on logic. Usually, NeSy techniques focus on learning the neural, probabilistic and/or fuzzy parameters of NeSy models. Learning the symbolic or logical structure of such models has, so far, received less attention. We introduce neurosymbolic decision trees (NDTs), as an extension of decision trees together with a novel NeSy structure learning algorithm, which we dub NeuID3. NeuID3 adapts the standard top-down induction of decision tree algorithms and combines it with a neural probabilistic logic representation, inherited from the DeepProbLog family of models. The key advantage of learning NDTs with NeuID3 is the support of both symbolic and subsymbolic data (such as images), and that they can exploit background knowledge during the induction of the tree structure, In our experimental evaluation we demonstrate the benefits of NeSys structure learning over more traditonal approaches such as purely data-driven learning with neural networks.