MILD: Multi-Intent Learning and Disambiguation for Proactive Failure Prediction in Intent-based Networking

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hossain, Md. Kamrul, Aljoby, Walid
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914331400077312
author Hossain, Md. Kamrul
Aljoby, Walid
author_facet Hossain, Md. Kamrul
Aljoby, Walid
contents In multi-intent intent-based networks, a single fault can trigger co-drift where multiple intents exhibit symptomatic KPI degradation, creating ambiguity about the true root-cause intent. We present MILD, a proactive framework that reformulates intent assurance from reactive drift detection to fixed-horizon failure prediction with intent-level disambiguation. MILD uses a teacher-augmented Mixture-of-Experts where a gated disambiguation module identifies the root-cause intent while per-intent heads output calibrated risk scores. On a benchmark with non-linear failures and co-drifts, MILD provides 3.8\%--92.5\% longer remediation lead time and improves intent-level root-cause disambiguation accuracy by 9.4\%--45.8\% over baselines. MILD also provides per-alert KPI explanations, enabling actionable diagnosis.
format Preprint
id arxiv_https___arxiv_org_abs_2602_14283
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MILD: Multi-Intent Learning and Disambiguation for Proactive Failure Prediction in Intent-based Networking
Hossain, Md. Kamrul
Aljoby, Walid
Networking and Internet Architecture
Machine Learning
In multi-intent intent-based networks, a single fault can trigger co-drift where multiple intents exhibit symptomatic KPI degradation, creating ambiguity about the true root-cause intent. We present MILD, a proactive framework that reformulates intent assurance from reactive drift detection to fixed-horizon failure prediction with intent-level disambiguation. MILD uses a teacher-augmented Mixture-of-Experts where a gated disambiguation module identifies the root-cause intent while per-intent heads output calibrated risk scores. On a benchmark with non-linear failures and co-drifts, MILD provides 3.8\%--92.5\% longer remediation lead time and improves intent-level root-cause disambiguation accuracy by 9.4\%--45.8\% over baselines. MILD also provides per-alert KPI explanations, enabling actionable diagnosis.
title MILD: Multi-Intent Learning and Disambiguation for Proactive Failure Prediction in Intent-based Networking
topic Networking and Internet Architecture
Machine Learning
url https://arxiv.org/abs/2602.14283