GABE: Groupwise Affine Basis Encoding

Introduce GABE (Groupwise Affine Basis Encoding) - a decomposition method that represents neural network weights as an addressable memory system. For any group of similar layers, we extract three interpretable components: a shared mean weight (long-term memory), a low-rank basis of variations (address space), and per-layer coefficients (pointers).

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-02-05
DOI
https://doi.org/10.5281/zenodo.18488811
Primary Topic
Adversarial Robustness in Machine Learning
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

GABE: Groupwise Affine Basis Encoding

Dmitry F. Feklin
Zenodo (CERN European Organization for Nuclear Research)
Adversarial Robustness in Machine Learning
article

GABE: Groupwise Affine Basis Encoding

Dmitry F. Feklin
article en

Abstract

Introduce GABE (Groupwise Affine Basis Encoding) - a decomposition method that represents neural network weights as an addressable memory system. For any group of similar layers, we extract three interpretable components: a shared mean weight (long-term memory), a low-rank basis of variations (address space), and per-layer coefficients (pointers).

Zenodo (CERN European Organization for Nuclear Research)
Openalex Percentile: Top 68%
Adversarial Robustness in Machine Learning
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

GABE: Groupwise Affine Basis Encoding — Dmitry F. Feklin · Zenodo (CERN European Organization for Nuclear Research) (2026) | TGRS Research Map | TGRS