How to Incorporate Monotonicity in Deep Networks While Preserving Flexibility?
read the original abstract
The importance of domain knowledge in enhancing model performance and making reliable predictions in the real-world is critical. This has led to an increased focus on specific model properties for interpretability. We focus on incorporating monotonic trends, and propose a novel gradient-based point-wise loss function for enforcing partial monotonicity with deep neural networks. While recent developments have relied on structural changes to the model, our approach aims at enhancing the learning process. Our model-agnostic point-wise loss function acts as a plug-in to the standard loss and penalizes non-monotonic gradients. We demonstrate that the point-wise loss produces comparable (and sometimes better) results on both AUC and monotonicity measure, as opposed to state-of-the-art deep lattice networks that guarantee monotonicity. Moreover, it is able to learn differentiated individual trends and produces smoother conditional curves which are important for personalized decisions, while preserving the flexibility of deep networks.
This paper has not been read by Pith yet.
Forward citations
Cited by 1 Pith paper
-
R&F-Inventory: A Large-Scale Dataset for Monotonic Inventory Estimation in Reach and Frequency Advertising
R&F-Inventory supplies complete budget-to-UV/PV curves for R&F contracts with built-in monotonicity and a theoretical exposure ceiling for quality checks, plus benchmarks for single-point prediction and curve reconstruction.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.