HAPEns: Hardware-Aware Post-Hoc Ensembling for Tabular Data

TL;DR

HAPEns is a novel hardware-aware post-hoc ensembling method for tabular data that optimally balances predictive accuracy and resource efficiency, outperforming existing baselines across numerous datasets.

Contribution

We introduce HAPEns, the first hardware-aware post-hoc ensembling approach that constructs diverse ensembles along the Pareto front for improved trade-offs.

Findings

HAPEns significantly outperforms baselines on 83 datasets.

Memory usage is a key objective for ensemble efficiency.

A static multi-objective weighting scheme enhances greedy ensembling methods.

Abstract

Ensembling is commonly used in machine learning on tabular data to boost predictive performance and robustness, but larger ensembles often lead to increased hardware demand. We introduce HAPEns, a post-hoc ensembling method that explicitly balances accuracy against hardware efficiency. Inspired by multi-objective and quality diversity optimization, HAPEns constructs a diverse set of ensembles along the Pareto front of predictive performance and resource usage. Existing hardware-aware post-hoc ensembling baselines are not available, highlighting the novelty of our approach. Experiments on 83 tabular classification datasets show that HAPEns significantly outperforms baselines, finding superior trade-offs for ensemble performance and deployment cost. Ablation studies also reveal that memory usage is a particularly effective objective metric. Further, we show that even a greedy ensembling algorithm can be significantly improved in this task with a static multi-objective weighting scheme.