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

TL;DR

MILD is a proactive framework for intent-based networks that predicts failures and disambiguates root causes, significantly reducing remediation time and improving diagnosis accuracy through a novel mixture-of-experts model.

Contribution

MILD introduces a new intent assurance approach using a teacher-augmented mixture-of-experts for proactive failure prediction and root-cause disambiguation in intent-based networks.

Findings

Provides 3.8-92.5% longer remediation lead time.

Improves root-cause disambiguation accuracy by 9.4-45.8%.

Enables actionable diagnosis with per-alert KPI explanations.

Abstract

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.