# SubQuad: Near-Quadratic-Free Structure Inference with Distribution-Balanced Objectives in Adaptive Receptor framework

arXiv: https://arxiv.org/abs/2602.17330 · HTML: https://mlsanity.com/paper/2602.17330/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 42 references that are in the map.
- First posted on arXiv 19 Feb 2026.

## Builds on (most cited first, 14 of 14)

- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [Algorithmic decision making and the cost of fairness](https://mlsanity.com/paper/1701.08230/) (2017)
- [Learning Discrete Structures for Graph Neural Networks](https://mlsanity.com/paper/1903.11960/) (2019)
- [ProtST: Multi-Modality Learning of Protein Sequences and Biomedical Texts](https://mlsanity.com/paper/2301.12040/) (2023)
- [xTrimoPGLM: Unified 100B-Scale Pre-trained Transformer for Deciphering the Language of Protein](https://mlsanity.com/paper/2401.06199/) (2024)
- [Beyond Locality-Sensitive Hashing](https://mlsanity.com/paper/1306.1547/) (2013)
- [Fairness, Semi-Supervised Learning, and More: A General Framework for Clustering with Stochastic Pairwise Constraints](https://mlsanity.com/paper/2103.02013/) (2021)
- [SOAR: Improved Indexing for Approximate Nearest Neighbor Search](https://mlsanity.com/paper/2404.00774/) (2024)
- [Multimodal Fusion Refiner Networks](https://mlsanity.com/paper/2104.03435/) (2021)
- [Doubly Constrained Fair Clustering](https://mlsanity.com/paper/2305.19475/) (2023)
- [Constrained Clustering: General Pairwise and Cardinality Constraints](https://mlsanity.com/paper/1907.10410/) (2019)
- [Fairness-enhancing mixed effects deep learning improves fairness on in- and out-of-distribution clustered (non-iid) data](https://mlsanity.com/paper/2310.03146/) (2023)
- [Diversifying the Genomic Data Science Research Community](https://mlsanity.com/paper/2201.08443/) (2022)
- [SEDD: Scalable and Efficient Dataset Deduplication with GPUs](https://mlsanity.com/paper/2501.01046/) (2025)

## Abstract (arXiv)

Comparative analysis of adaptive immune repertoires at population scale is hampered by two practical bottlenecks: the near-quadratic cost of pairwise affinity evaluations and dataset imbalances that obscure clinically important minority clonotypes. We introduce SubQuad, an end-to-end pipeline that addresses these challenges by combining antigen-aware, near-subquadratic retrieval with GPU-accelerated affinity kernels, learned multimodal fusion, and fairness-constrained clustering. The system employs compact MinHash prefiltering to sharply reduce candidate comparisons, a differentiable gating module that adaptively weights complementary alignment and embedding channels on a per-pair basis, and an automated calibration routine that enforces proportional representation of rare antigen-specific subgroups. On large viral and tumor repertoires SubQuad achieves measured gains in throughput and peak memory usage while preserving or improving recall@k, cluster purity, and subgroup equity. By co-designing indexing, similarity fusion, and equity-aware objectives, SubQuad offers a scalable, bias-aware platform for repertoire mining and downstream translational tasks such as vaccine target prioritization and biomarker discovery.