A Vector Symbolic Approach to Multiple Instance Learning

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Dhrubo, Ehsan Ahmed, Alam, Mohammad Mahmudul, Raff, Edward, Oates, Tim, Holt, James
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915629585399808
author Dhrubo, Ehsan Ahmed
Alam, Mohammad Mahmudul
Raff, Edward
Oates, Tim
Holt, James
author_facet Dhrubo, Ehsan Ahmed
Alam, Mohammad Mahmudul
Raff, Edward
Oates, Tim
Holt, James
contents Multiple Instance Learning (MIL) tasks impose a strict logical constraint: a bag is labeled positive if and only if at least one instance within it is positive. While this iff constraint aligns with many real-world applications, recent work has shown that most deep learning-based MIL approaches violate it, leading to inflated performance metrics and poor generalization. We propose a novel MIL framework based on Vector Symbolic Architectures (VSAs), which provide a differentiable mechanism for performing symbolic operations in high-dimensional space. Our method encodes the MIL assumption directly into the model's structure by representing instances and concepts as nearly orthogonal high-dimensional vectors and using algebraic operations to enforce the iff constraint during classification. To bridge the gap between raw data and VSA representations, we design a learned encoder that transforms input instances into VSA-compatible vectors while preserving key distributional properties. Our approach, which includes a VSA-driven MaxNetwork classifier, achieves state-of-the-art results for a valid MIL model on standard MIL benchmarks and medical imaging datasets, outperforming existing methods while maintaining strict adherence to the MIL formulation. This work offers a principled, interpretable, and effective alternative to existing MIL approaches that rely on learned heuristics.
format Preprint
id arxiv_https___arxiv_org_abs_2511_16795
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Vector Symbolic Approach to Multiple Instance Learning
Dhrubo, Ehsan Ahmed
Alam, Mohammad Mahmudul
Raff, Edward
Oates, Tim
Holt, James
Machine Learning
Multiple Instance Learning (MIL) tasks impose a strict logical constraint: a bag is labeled positive if and only if at least one instance within it is positive. While this iff constraint aligns with many real-world applications, recent work has shown that most deep learning-based MIL approaches violate it, leading to inflated performance metrics and poor generalization. We propose a novel MIL framework based on Vector Symbolic Architectures (VSAs), which provide a differentiable mechanism for performing symbolic operations in high-dimensional space. Our method encodes the MIL assumption directly into the model's structure by representing instances and concepts as nearly orthogonal high-dimensional vectors and using algebraic operations to enforce the iff constraint during classification. To bridge the gap between raw data and VSA representations, we design a learned encoder that transforms input instances into VSA-compatible vectors while preserving key distributional properties. Our approach, which includes a VSA-driven MaxNetwork classifier, achieves state-of-the-art results for a valid MIL model on standard MIL benchmarks and medical imaging datasets, outperforming existing methods while maintaining strict adherence to the MIL formulation. This work offers a principled, interpretable, and effective alternative to existing MIL approaches that rely on learned heuristics.
title A Vector Symbolic Approach to Multiple Instance Learning
topic Machine Learning
url https://arxiv.org/abs/2511.16795