TL;DR
ARM-Net is a novel neural network designed for structured data that adaptively models feature interactions, improving accuracy and interpretability over existing methods by selectively focusing on relevant cross features.
Contribution
The paper introduces ARM-Net, a new adaptive relation modeling network that dynamically selects and models feature interactions for structured data, enhancing both performance and interpretability.
Findings
ARM-Net outperforms existing models on real-world datasets.
It provides more interpretable predictions for decision making.
The sparse attention mechanism effectively filters noisy features.
Abstract
Relational databases are the de facto standard for storing and querying structured data, and extracting insights from structured data requires advanced analytics. Deep neural networks (DNNs) have achieved super-human prediction performance in particular data types, e.g., images. However, existing DNNs may not produce meaningful results when applied to structured data. The reason is that there are correlations and dependencies across combinations of attribute values in a table, and these do not follow simple additive patterns that can be easily mimicked by a DNN. The number of possible such cross features is combinatorial, making them computationally prohibitive to model. Furthermore, the deployment of learning models in real-world applications has also highlighted the need for interpretability, especially for high-stakes applications, which remains another issue of concern to DNNs. In…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
MethodsARM-Net
