Minjae Rhee
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Minjae Rhee has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Jie Si Yang
The University of Utah, Salt Lake City, UT, USA
2 shared publications Jitong Zou
Case Western Reserve University
2 shared publications- Zixuan Guo
New York University
2 shared publications - Aowei Shen
University of Washington
1 shared publication - Changhao Zhang
The University of Chicago
1 shared publication - Dai Teng
University of Illinois at Urbana–Champaign
1 shared publication
Latest Publications
- Open Access
- 14 September 2026
- Published by Elsevier in SSRN Electronic Journal
ProHeal: Predictive Self-Healing through Event-Onset Forecasting, Block-Calibrated Risk Gating, and Constrained Remediation Replay for Cloud Infrastructure
Self-healing infrastructure is useful only when it acts before a service-impacting event and when the action itself does not create a larger disturbance. Existing telemetry anomaly detectors mostly answer whether a system is abnormal now ; conversely, many self-healing architectures leave the predictive trigger and remediation policy underspecified. This paper introduces ProHeal, a concrete predictive self-healing method that couples event-onset forecasting with a risk-controlled alert gate and a disruption-constrained remediation policy. First, ProHeal formulates failure forecasting as predicting the onset of a labeled operational anomaly within a future horizon while explicitly excluding already-abnormal states. A robust multi-resolution precursor encoder combines normalized state, absolute deviation, 5/15/30-minute mean shifts, 15-minute volatility, and sparse global deviation summaries. A LightGBM hazard learner then estimates multi-horizon onset risk. Second, a block-max conformal gate converts scores into alert episodes under an explicit exceedance budget, reducing sensitivity to isolated correlated score spikes. Third, a matchedstate drain/migration policy selects a healthy historical continuation subject to a boundary-disruption constraint; a PCA residual model trained only on normal training telemetry provides an independent health-risk evaluator for counterfactual replay. Experiments use two real, publicly downloadable industrial servermonitoring sources: eBay Pooled Server Metrics (PSM) and three representative Server Machine Dataset (SMD) entities. All splits are chronological. On PSM, ProHeal attains AUPRC 0.0127, 0.0684, and 0.0883 for 5-, 15-, and 30-minute onset forecasting, respectively, corresponding to 2.26×, 1.94×, and 2.09× the AUPRC of a strong LightGBM lag-feature baseline. At the primary 15-minute operating point (α = 0.03), the gate generates 0.784 false alert episodes per 1000 healthy minutes and detects 11.1% of test events with a median four-minute lead. Across three SMD entities, the method is strongest in AUPRC on one entity, second-tier on another, and weak on the sparsest one, documenting cross-entity heterogeneity rather than masking it. Ablation identifies windowed mean shifts, volatility, and global deviation summaries as the dominant predictive components. Under 2% Gaussian telemetry noise and 2% random missingness, 15-minute PSM AUPRC remains 0.0472 and 0.0509. Finally, in a policy-only replay over 18 PSM test events, constrained matched-state drain reduces independent mean health risk by 65.7% relative to no action while using 45.0% less boundary disruption than random drain; 88.9% of events have a candidate satisfying the primary disruption budget. Code, exact result tables, data-download instructions, and cryptographic hashes accompany the paper.
- 14 September 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessProHeal: Predictive Self-Healing through Event-Onset Forecasting, Block-Calibrated Risk Gating, and Constrained Remediation Replay for Cloud Infrastructure
Self-healing infrastructure is useful only when it acts before a service-impacting event and when the action itself does not create a larger disturbance. Existing telemetry anomaly detectors mostly answer whether a system is abnormal now ; conversely, many self-healing architectures leave the predictive trigger and remediation policy underspecified. This paper introduces ProHeal, a concrete predictive self-healing method that couples event-onset forecasting with a risk-controlled alert gate and a disruption-constrained remediation policy. First, ProHeal formulates failure forecasting as predicting the onset of a labeled operational anomaly within a future horizon while explicitly excluding already-abnormal states. A robust multi-resolution precursor encoder combines normalized state, absolute deviation, 5/15/30-minute mean shifts, 15-minute volatility, and sparse global deviation summaries. A LightGBM hazard learner then estimates multi-horizon onset risk. Second, a block-max conformal gate converts scores into alert episodes under an explicit exceedance budget, reducing sensitivity to isolated correlated score spikes. Third, a matchedstate drain/migration policy selects a healthy historical continuation subject to a boundary-disruption constraint; a PCA residual model trained only on normal training telemetry provides an independent health-risk evaluator for counterfactual replay. Experiments use two real, publicly downloadable industrial servermonitoring sources: eBay Pooled Server Metrics (PSM) and three representative Server Machine Dataset (SMD) entities. All splits are chronological. On PSM, ProHeal attains AUPRC 0.0127, 0.0684, and 0.0883 for 5-, 15-, and 30-minute onset forecasting, respectively, corresponding to 2.26×, 1.94×, and 2.09× the AUPRC of a strong LightGBM lag-feature baseline. At the primary 15-minute operating point (α = 0.03), the gate generates 0.784 false alert episodes per 1000 healthy minutes and detects 11.1% of test events with a median four-minute lead. Across three SMD entities, the method is strongest in AUPRC on one entity, second-tier on another, and weak on the sparsest one, documenting cross-entity heterogeneity rather than masking it. Ablation identifies windowed mean shifts, volatility, and global deviation summaries as the dominant predictive components. Under 2% Gaussian telemetry noise and 2% random missingness, 15-minute PSM AUPRC remains 0.0472 and 0.0509. Finally, in a policy-only replay over 18 PSM test events, constrained matched-state drain reduces independent mean health risk by 65.7% relative to no action while using 45.0% less boundary disruption than random drain; 88.9% of events have a candidate satisfying the primary disruption budget. Code, exact result tables, data-download instructions, and cryptographic hashes accompany the paper.
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 158232-158252
A Dual-Process Memory-Augmented Large Language Model Agent for Explainable Sequential Recommendation
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 158232-158252
Open AccessA Dual-Process Memory-Augmented Large Language Model Agent for Explainable Sequential Recommendation
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 146019-146040
PRESAGE: Uncertainty-Aware Predictive Elastic Scheduling for Cloud Analytics and GenAI Inference
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 146019-146040
Open AccessPRESAGE: Uncertainty-Aware Predictive Elastic Scheduling for Cloud Analytics and GenAI Inference
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 138096-138116
Closed-Loop Audio Neuroregulation for ADHD: Graph-Based Attention Decoding and Rhythm Entrainment
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 138096-138116
Open AccessClosed-Loop Audio Neuroregulation for ADHD: Graph-Based Attention Decoding and Rhythm Entrainment
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 115695-115709
Enhancing Web Search Agents With Self-Play Contrastive Fine-Tuning
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 115695-115709
Open AccessEnhancing Web Search Agents With Self-Play Contrastive Fine-Tuning
- Top Cited PapersOpen Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 111086-111102
Self-Evolving AI Agents With Dual Memory for Automated Software Testing and Bug Localization
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 111086-111102
Top Cited PapersOpen AccessSelf-Evolving AI Agents With Dual Memory for Automated Software Testing and Bug Localization