Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Md. Kamrul Hossain, Walid Aljoby

TL;DR

MILD, a proactive framework that reformulates intent assurance from reactive drift detection to fixed-horizon failure prediction with intent-level disambiguation with intent-level disambiguation, is presented.

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.

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

TL;DR

MILD, a proactive framework that reformulates intent assurance from reactive drift detection to fixed-horizon failure prediction with intent-level disambiguation with intent-level disambiguation, is presented.

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.
Paper Structure (16 sections, 7 equations, 5 figures, 2 tables)

This paper contains 16 sections, 7 equations, 5 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. The MILD Framework
  4. Problem Formulation and Fixed-Horizon Labels
  5. Teacher-Augmented MoE and Hybrid Training
  6. Runtime Alerting and Operational Intelligence
  7. Experimental Results
  8. Dataset Generation
  9. Implementation and Training Details
  10. Performance Analysis of MILD
  11. Cross-validation outcome
  12. Disambiguation
  13. Per-Alert Explainability via SHAP
  14. Dynamic Lead Time Estimation with Multi-Horizon Models
  15. Comparison with Baselines
  16. ...and 1 more sections

Figures (5)

  • Figure 1: MILD: teacher-augmented MoE with risk prediction, root-cause disambiguation, and per-alert intelligence.
  • Figure 2: MILD's disambiguation during a co-drift event. Smoothed risk scores (left y-axis) and gating probabilities (right y-axis) are shown for the root cause (analytics, red) and the victim (telemetry, blue) intents.
  • Figure 3: Example SHAP explanation for a telemetry alert (feature contributions to risk score).
  • Figure 4: Multi-horizon alerting for a telemetry event (H=120,60,30).
  • Figure 5: Normalized holistic comparison: detection, lead time, reliability (inverted FP), and root-cause accuracy.