# Hippasus: Accurate and Cost-Efficient Feature Augmentation over Relational Tables

DevFeed: [Hippasus: Accurate and Cost-Efficient Feature Augmentation over Relational Tables](<https://devfeed.tech/articles/hippasus-accurate-and-cost-efficient-feature-augmentation-over-relational-tables-132667.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2602.02025>)

Author: Serafeim Papadias, Kostas Patroumpas, Dimitrios Skoutas

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Databases](<https://devfeed.tech/sources/arxiv-databases.md>)

Topics: [Feature Engineering](<https://devfeed.tech/topics/feature-engineering.md>), [JOIN](<https://devfeed.tech/topics/join.md>), [rdbms](<https://devfeed.tech/topics/rdbms.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [Predictive AI](<https://devfeed.tech/topics/predictive-ai.md>), [Plover](<https://devfeed.tech/topics/plover.md>)

Tags: [adaptive](<https://devfeed.tech/tags/adaptive.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [challenges](<https://devfeed.tech/tags/challenges.md>), [complex](<https://devfeed.tech/tags/complex.md>), [cost](<https://devfeed.tech/tags/cost.md>), [cross](<https://devfeed.tech/tags/cross.md>), [cs-db](<https://devfeed.tech/tags/cs-db.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [data](<https://devfeed.tech/tags/data.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [efficiency](<https://devfeed.tech/tags/efficiency.md>), [execution](<https://devfeed.tech/tags/execution.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [exploration](<https://devfeed.tech/tags/exploration.md>), [exploring](<https://devfeed.tech/tags/exploring.md>), [feature](<https://devfeed.tech/tags/feature.md>), [feature-selection](<https://devfeed.tech/tags/feature-selection.md>), [features](<https://devfeed.tech/tags/features.md>), [framework](<https://devfeed.tech/tags/framework.md>), [hybrid](<https://devfeed.tech/tags/hybrid.md>), [tables](<https://devfeed.tech/tags/tables.md>)

## AI overview

Hippasus augments a base table with predictive features from related tables while controlling the cost of exploring join paths. It ranks candidate paths before running joins, using lightweight statistical signals and adaptive semantic analysis that calls an LLM only when needed. Multi-way joins and cross-path feature consolidation support execution; hybrid feature selection combines statistical relevance with semantic refinement. Across 13 real-world datasets, the authors report up to 15.7% average predictive-performance improvement over state-of-the-art methods, runtime on par with the fastest methods, and low LLM token cost. These claims are limited to the abstract; it does not provide details on datasets, metrics, or evaluation conditions.

## Source excerpt

arXiv:2602.02025v3 Announce Type: replace Abstract: ML models critically depend on feature quality, yet in real-world settings, useful features are often distributed across multiple relational tables rather than a single dataset. Feature augmentation addresses this problem by automatically discovering and joining additional tables to enrich a base table with predictive features. However, scaling feature augmentation to complex schemas with many tables and multi-hop relationships is challenging. It requires exploring a large space of join paths, executing costly joins, and selecting useful features from noisy results. Existing approaches suffer from either limited effectiveness or efficiency. Restricting exploration to simple joins limits predictive performance, while more expressive methods rely on expensive training data, lack scalability, or fail to fully exploit schema-level semantics. We present Hippasus, a cost-aware, LLM-guided feature augmentation framework over relational schemas, that addresses these challenges. Hippasus ranks candidate join paths before executing any join, by combining lightweight statistical signals with adaptive semantic analysis, invoking an LLM only when necessary. It further introduces efficient multi-way join execution with cross-path feature consolidation, and a hybrid feature selection strategy that integrates statistical relevance with semantic refinement. Experiments on 13 real-world datasets show that Hippasus improves predictive performance by up to 15.7% on average over state-of-the-art methods, while running on par with the fastest of them and keeping its LLM token cost low.