arXiv：cs.LG· Radha Poovendran, Andrea Stocco, Linda Bushnell·· 3 小时前AI 评分30
AIBL：结合结构化记忆与神经嵌入的增强型实例学习
AIBL: Augmented Instance-Based Learning with Structured Memory and Neural Embeddings
AI 导读
研究者提出 AIBL（Augmented Instance-Based Learning），一种在学习向量空间中构建的实例学习模型，将 IBLT 的符号化情境匹配泛化为神经嵌入相似度，同时保留实例存储、激活加权检索与效用混合机制。
正文
Abstract:Sequential learning systems often make decisions from accumulated experience while receiving high-dimensional inputs whose distribution may change over time. Instance-Based Learning Theory (IBLT) provides a principled case-based framework for such settings through stored situation-decision-utility instances, partial matching, activation, and blending. IBLT relies on symbolic knowledge representation in dictionary-like formats, but text, images, transaction vectors, and user-item histories often require learned similarity rather than hand-specified matching rules. In this paper, we introduce AIBL (Augmented Instance-Based Learning), an instance-learning model formulated in a learned vector space for high- dimensional sequential data. AIBL generalizes symbolic situation matching to neural embedding similarity while retaining instance storage, activation- weighted retrieval, and utility blending. The AIBL model organizes memory into active, forgotten, and surprise stores. Surprise memory separates weakly matched, possible out-of-distribution, or corner-case observations from active memory, reducing forced fitting to the nearest available cases. An observation-driven graduation algorithm promotes recurring surprise instances to active memory, allowing the memory to incorporate repeated novel patterns that may arise under concept drift. We evaluate the same implementation on five machine learning tasks and three controlled simulation tasks, comparing AIBL with classical IBLT variants and task-specific baselines where appropriate. AIBL improves accuracy by 6 to 17 percentage points. The results show where vector-space retrieval improves over symbolic matching and how the added memory mechanisms govern novelty detection, cold-start handling, drift adaptation, and reward learning under the tested protocols.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.03413 [cs.LG] |
| (or arXiv:2610.03413v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.03413 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Andrea Stocco [view email]
[v1]
Fri, 2 Oct 2026 15:00:48 UTC (55 KB)
来源：arXiv：cs.LG · arxiv.org