---
title: "Reciprocity Can Erase Direction:tructural Boundaries and Controlled Utility of Magnetic Graph Networks"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.04295v1"
permalink: "https://feed.astralor.com/items/itm_77f44e398b107ab0b4ebdec4"
published: "2026-11-03T04:21:29.000Z"
score: 59
channel: "tech"
tags: ["Reciprocity Can Erase","Direction","Boundaries","Controlled Utility","Magnetic Graph Networks","Magnetic","Laplacians","Exact"]
---

# Reciprocity Can Erase Direction:tructural Boundaries and Controlled Utility of Magnetic Graph Networks

## At a glance

Magnetic graph networks encode direction through phase, but a learned graph can erase the intended directional mechanism before prediction. We characterize this failure for support-based magnetic Laplacians. Exact ident…

## Key points

- Magnetic graph networks encode direction through phase, but a learned graph can erase the intended directional mechanism before prediction.
- We characterize this failure for support-based magnetic Laplacians.
- Exact identities relate imaginary energy and distance from zero phase to amplitude-weighted reciprocity.

## Full text

Magnetic graph networks encode direction through phase, but a learned graph can erase the intended directional mechanism before prediction. We characterize this failure for support-based magnetic Laplacians. Exact identities relate imaginary energy and distance from zero phase to amplitude-weighted reciprocity. Top-$k$ selection forces complete collapse when the observed-node count satisfies $m\leq k+1$, and dense support imposes a lower bound on reciprocal-arc fraction. We then construct paired propagation examples with identical node features and symmetric amplitudes but opposite labels, giving a provable chance-level limit for direction-erasing representations. In 72 fixed neural fits, support phase achieved test AUROC 1.0000 on a unilateral ring but 0.5000 on reciprocal ring and complete supports; continuous score phase and a real directed comparator achieved 1.0000 throughout. All models solved the direction-free control. These are oracle-direction mechanism tests, not evidence of learned clinical direction. In the preserved public DeepDRiD development study, continuous phase was active but its robustness difference from zero phase was only $+0.0036$ (descriptive 95\% interval $-0.0014$ to $+0.0095$) on validation patients used for checkpoint selection. The contribution is a structural and experimental framework for distinguishing erased direction from unestablished task utility. It provides a precise circumstance in which magnetic phase preserves useful information, without asserting universal or clinical superiority.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_77f44e398b107ab0b4ebdec4