Mixing Configurations for Downstream Prediction

Juntang Wang, Hao Wu, Yihan Wang, Dongmian Zou, Shixin Xu
Proceedings of the 43rd International Conference on Machine Learning, PMLR 306:131247-131262, 2026.

Abstract

Clustering-based features are widely used in machine learning, but most methods must choose a resolution—a choice that is global, fixed, and ad hoc. Recent work shows that varying the resolution parameter produces only a finite set of structurally stable partitions, known as configurations. Based on this, we introduce Configuration-Mixed Prediction (CMP), a setting where models learn to adaptively weight these configurations per sample for downstream prediction. We propose MixConfig, a plug-and-play feature augmentation module that extracts configurations from any embedding and learns energy-aware mixing weights via a novel selector that jointly reasons about sample context, cluster assignments, and stability statistics. Experiments across tabular, molecular, vision, and text domains demonstrate consistent improvements over single-resolution and static baselines across diverse predictor architectures, with gains particularly pronounced in low-data regimes.

Cite this Paper


BibTeX
@InProceedings{pmlr-v306-wang26iz, title = {Mixing Configurations for Downstream Prediction}, author = {Wang, Juntang and Wu, Hao and Wang, Yihan and Zou, Dongmian and Xu, Shixin}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, pages = {131247--131262}, year = {2026}, editor = {Zhang, Tong and Dudik, Miroslav and Jaggi, Martin and Agarwal, Alekh and Li, Sharon and Schuurmans, Dale and Zhu, Jerry and Berkenkamp, Felix and Dong, Hanze and Bietti, Alberto}, volume = {306}, series = {Proceedings of Machine Learning Research}, month = {06--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v306/main/assets/wang26iz/wang26iz.pdf}, url = {https://proceedings.mlr.press/v306/wang26iz.html}, abstract = {Clustering-based features are widely used in machine learning, but most methods must choose a resolution—a choice that is global, fixed, and ad hoc. Recent work shows that varying the resolution parameter produces only a finite set of structurally stable partitions, known as configurations. Based on this, we introduce Configuration-Mixed Prediction (CMP), a setting where models learn to adaptively weight these configurations per sample for downstream prediction. We propose MixConfig, a plug-and-play feature augmentation module that extracts configurations from any embedding and learns energy-aware mixing weights via a novel selector that jointly reasons about sample context, cluster assignments, and stability statistics. Experiments across tabular, molecular, vision, and text domains demonstrate consistent improvements over single-resolution and static baselines across diverse predictor architectures, with gains particularly pronounced in low-data regimes.} }
Endnote
%0 Conference Paper %T Mixing Configurations for Downstream Prediction %A Juntang Wang %A Hao Wu %A Yihan Wang %A Dongmian Zou %A Shixin Xu %B Proceedings of the 43rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2026 %E Tong Zhang %E Miroslav Dudik %E Martin Jaggi %E Alekh Agarwal %E Sharon Li %E Dale Schuurmans %E Jerry Zhu %E Felix Berkenkamp %E Hanze Dong %E Alberto Bietti %F pmlr-v306-wang26iz %I PMLR %P 131247--131262 %U https://proceedings.mlr.press/v306/wang26iz.html %V 306 %X Clustering-based features are widely used in machine learning, but most methods must choose a resolution—a choice that is global, fixed, and ad hoc. Recent work shows that varying the resolution parameter produces only a finite set of structurally stable partitions, known as configurations. Based on this, we introduce Configuration-Mixed Prediction (CMP), a setting where models learn to adaptively weight these configurations per sample for downstream prediction. We propose MixConfig, a plug-and-play feature augmentation module that extracts configurations from any embedding and learns energy-aware mixing weights via a novel selector that jointly reasons about sample context, cluster assignments, and stability statistics. Experiments across tabular, molecular, vision, and text domains demonstrate consistent improvements over single-resolution and static baselines across diverse predictor architectures, with gains particularly pronounced in low-data regimes.
APA
Wang, J., Wu, H., Wang, Y., Zou, D. & Xu, S.. (2026). Mixing Configurations for Downstream Prediction. Proceedings of the 43rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 306:131247-131262 Available from https://proceedings.mlr.press/v306/wang26iz.html.

Related Material