Unison framework improves learning from scored item groups

UNISON: A Unified Framework for Learning from Scored Bags

Machine Learning

Summary

Some tasks involve learning from collections of items that each have a score, such as recommending products or classifying groups in biology. This paper presents UNISON, a single approach that handles these tasks by learning item features, personalizing preferences for each group, and then predicting group-level outcomes. The authors show this method works well across different fields and is efficient and interpretable. They also prove theoretical properties that support its design and show it deals effectively with new, unseen groups.

What this means in practice

  • For entertainment platform engineers: Develop recommendation algorithms that efficiently predict user preferences from item-score group data in book and movie platforms.
  • For bioinformatics analysts: Classify complex biological data sets like T cell receptor repertoires or microbiomes by modeling group-specific preference patterns from scored item collections.

Authors

Ofek Kirshenboim, Or Shkuri, Shani Finkelshtein, Yoram Louzoun

Abstract

We introduce UNISON, a unified framework that bridges multiple instance learning and recommendation systems by treating both as instances of learning from scored bag collections of (item, score) pairs. Unlike traditional approaches that address bag-level classification and personalized recommendation as separate problems, UNISON decomposes learning into three interconnected stages: (1) learning universal item representations, (2) modeling bag-specific preference patterns through lightweight personalized parameters, and (3) inferring bag-level characteristics from learned preferences. We justify the architectural choice of linear bag-specific scoring through a first-order analysis: when item embeddings are sufficiently smooth in the score, a linear function approximates the score up to a Taylor remainder controlled by the curvature of the underlying preference function. For cold-start scenarios, we show that the cold-bag fitting problem reduces to ridge-less linear regression with a closed-form solution, and provide convergence guarantees for the iterative variant. Empirically, UNISON matches or outperforms state-of-the-art approaches across diverse domains: entertainment (books, movies), immunology (T cell receptor (TCR) based classification), and microbiome, offering superior computational efficiency and interpretability. A controlled synthetic experiment further confirms that the bag-specific parameters ($w_j, b_j$) recover the latent factors that drive item scores even when the projection $φ$ has no access to the original scoring mechanism (AUC > 0.998). UNISON is available at https://github.com/louzounlab/UNISON.