Interpretable Set Functions
This provides a more interpretable alternative to black-box models for tasks involving set aggregation, though it appears incremental in its approach.
The paper tackles the problem of learning interpretable set functions for aggregating variable-length feature sets, achieving accuracy comparable to deep sets and deep neural networks while being easier to debug and understand.
We propose learning flexible but interpretable functions that aggregate a variable-length set of permutation-invariant feature vectors to predict a label. We use a deep lattice network model so we can architect the model structure to enhance interpretability, and add monotonicity constraints between inputs-and-outputs. We then use the proposed set function to automate the engineering of dense, interpretable features from sparse categorical features, which we call semantic feature engine. Experiments on real-world data show the achieved accuracy is similar to deep sets or deep neural networks, and is easier to debug and understand.