mlsanityData to 7 Oct 2026

Explainable Heterogeneous Anomaly Detection in Financial Networks via Adaptive Expert Routing

arXiv 2510.17088 ↗First posted 20 Oct 2025cs.LG cs.AI cs.CEcited by 0

Not on the map. Why?

Abstract (arXiv)

Financial anomalies arise from heterogeneous mechanisms - price shocks, liquidity freezes, contagion cascades, and momentum reversals - yet existing detectors produce uniform anomaly scores without revealing which mechanism is failing or where risks concentrate. This hinders targeted responses: liquidity freezes call for market-making support, whereas price shocks from information asymmetry call for circuit breakers. Three key challenges remain unresolved: (1) static graph structures cannot adapt when correlations shift across regimes; (2) uniform detectors overlook heterogeneous anomaly signatures; and (3) black-box scores provide no actionable guidance on which mechanism drives the anomaly. We address these challenges with an adaptive graph learning framework that embeds interpretability architecturally rather than post hoc. The framework constructs stress-modulated graphs that adaptively interpolate between known sector and geographic relationships and data-driven correlations as market conditions evolve. Anomalies are decomposed via four mechanism-specific experts - Price-Shock, Liquidity, Systemic-Contagion, and Momentum-Reversal - whose routing weights serve as interpretable proxies for mechanism attribution. A hierarchical Market Pressure Index aggregates entity-level anomaly scores into graduated market-wide alerts. On 100 U.S. equities (2017-2024), the framework detects all six major market stress events with a 3.7-day mean lead time, outperforming the strongest baselines by +33 percentage points in detection rate (AUC 0.888, AP 0.626). Case studies on the SVB collapse (March 2023) and Japan carry-trade unwind (August 2024) demonstrate that routing weights automatically distinguish localized sector-specific crises from systemic multi-sector propagation - without labeled supervision.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 28 of its 60 references that are in the map. First posted on arXiv 20 Oct 2025.

Builds on

28 of 60 references.

References · 28

  1. 2017Attention Is All You Needcited by 59,932
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2017Graph Attention Networkscited by 8,854
  4. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  5. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,413
  6. 2021Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsitycited by 3,014
  7. 2021Scaling Vision with Sparse Mixture of Expertscited by 740
  8. 2019EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphscited by 443
  9. 2021Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancycited by 387
  10. 2021Graph Neural Network-Based Anomaly Detection in Multivariate Time Seriescited by 300
  11. 2020Why Normalizing Flows Fail to Detect Out-of-Distribution Datacited by 220
  12. 2016LSTM-based Encoder-Decoder for Multi-sensor Anomaly Detectioncited by 213
16 more
  1. 2022TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Datacited by 211
  2. 2021Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learningcited by 175
  3. 2020Multivariate Time-series Anomaly Detection via Graph Attention Networkcited by 165
  4. 2023Towards Better Dynamic Graph Learning: New Architecture and Unified Librarycited by 154
  5. 2023A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detectioncited by 145
  6. 2022ROLAND: Graph Learning Framework for Dynamic Graphscited by 131
  7. 2023DCdetector: Dual Attention Contrastive Representation Learning for Time Series Anomaly Detectioncited by 103
  8. 2024UniTS: A Unified Multi-Task Time Series Modelcited by 93
  9. 2020AnomalyDAE: Dual autoencoder for anomaly detection on attributed networkscited by 81
  10. 2023Mixture-of-Experts Meets Instruction Tuning:A Winning Combination for Large Language Modelscited by 65
  11. 2022Evaluation of post-hoc interpretability methods in time-series classificationcited by 53
  12. 2023MEMTO: Memory-guided Transformer for Multivariate Time Series Anomaly Detectioncited by 26
  13. 2024Graph Neural Networks for Financial Fraud Detection: A Reviewcited by 24
  14. 2024Graph Mixture of Experts and Memory-augmented Routers for Multivariate Time Series Anomaly Detectioncited by 19
  15. 2023A Comprehensive Review on Financial Explainable AIcited by 10
  16. 2022DyG2Vec: Efficient Representation Learning for Dynamic Graphscited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Inferring Latent Market Forces: Evaluating LLM Detection of Gamma Exposure Patterns via Obfuscation Testing
  2. 2026A Multi-Scale Graph Learning Framework with Temporal Consistency Constraints for Financial Fraud Detection in Transaction Networks under Non-Stationary Conditions
  3. 2026EvoTS-Agent: A Self-Evolving LLM Agent for Financial Time Series Change Point Detection
  4. 2026Contagion on the Trading Floor: How Adversarial Signals Spread in Multi-Agent Trading Systems
  5. 2026From Accuracy to Auditability: A Survey of Determinism in Financial AI Systems
  6. 2026Federated Graph AGI for Cross-Border Insider Threat Intelligence in Government Financial Schemes
  7. 2026TRACE: Temporal Rule-Anchored Chain-of-Evidence on Knowledge Graphs for Interpretable Stock Movement Prediction
  8. 2025FinCARE: Financial Causal Analysis with Reasoning and Evidence