Detecting High-Potential SMEs with Heterogeneous Graph Neural Networks

• URL: http://arxiv.org/abs/2602.19591v2
• Date: Fri, 27 Feb 2026 06:35:57 GMT
• Title: Detecting High-Potential SMEs with Heterogeneous Graph Neural Networks
• Abstract summary: Small and Medium Enterprises (SMEs) constitute 99.9% of U.S. businesses and generate 44% of economic activity.<n>We introduce SME-HGT, a Heterogeneous Graph Transformer framework that predicts which Phase I awardees will advance to Phase II funding using exclusively public data.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Small and Medium Enterprises (SMEs) constitute 99.9% of U.S. businesses and generate 44% of economic activity, yet systematically identifying high-potential SMEs remains an open challenge. We introduce SME-HGT, a Heterogeneous Graph Transformer framework that predicts which SBIR Phase I awardees will advance to Phase II funding using exclusively public data. We construct a heterogeneous graph with 32,268 company nodes, 124 research topic nodes, and 13 government agency nodes connected by approximately 99,000 edges across three semantic relation types. SME-HGT achieves an AUPRC of 0.621 0.003 on a temporally-split test set, outperforming an MLP baseline (0.590 0.002) and R-GCN (0.608 0.013) across five random seeds. At a screening depth of 100 companies, SME-HGT attains 89.6% precision with a 2.14 lift over random selection. Our temporal evaluation protocol prevents information leakage, and our reliance on public data ensures reproducibility. These results demonstrate that relational structure among firms, research topics, and funding agencies provides meaningful signal for SME potential assessment, with implications for policymakers and early-stage investors.

Related papers

• Modality-Decoupled Federated Learning for Privacy-Preserving Embodied Intelligence in 6G [90.42669277637026]
  Sixth-generation (6G) wireless networks are expected to provide a key infrastructure for large-scale embodied intelligence.<n>This article proposes FedMVLA, a modality-decoupled FL framework for privacy-preserving embodied intelligence in 6G networks.
  arXiv  Detail & Related papers  (2026-09-09T01:36:44Z)
• Marginal Fidelity Does Not Establish User Simulation in Demographic Synthetic Survey Panels: Response Contracts, Support Collapse and Conditioning Failure [51.736723807086385]
  Population-marginal agreement is evidence about an elicitation contract and an estimand obtainable without simulated respondents, not evidence of individual simulation.<n>On nine aligned model-battery pairs, a no-persona population-prevalence query averages 6.27 MAE versus 12.39 for committed panels and wins all nine comparisons.
  arXiv  Detail & Related papers  (2026-09-07T10:22:22Z)
• Explainable Machine Learning for Broadband Adoption Disparities: Tract-Level Prediction and SHAP-Based Factor Profiling [6.076837441966713]
  The United States has allocated approximately $65 billion through the Infrastructure Investment and Jobs Act for broadband expansion.<n>This paper presents an explainable machine learning framework for profiling broadband adoption disparities across 83,359 tracts nationwide.
  arXiv  Detail & Related papers  (2026-08-29T07:39:08Z)
• Planetary Prediction Engine: Autonomous Geospatial Prediction via Intelligent Data Selection and Foundation Model Embeddings [8.285606894669046]
  We present the Planetary Prediction Engine (PPE), an autonomous AI system that executes this end-to-end workflow from natural-language queries.<n>PPE synthesizes multimodal datasets on the fly, retrieving relevant co variables across open-web and Earth observation platforms.<n>PPE consistently outperforms state-of-the-art or manually tuned expert baselines.
  arXiv  Detail & Related papers  (2026-08-26T17:50:52Z)
• Accounting Graph Transformer for Short-History Multi-KPI Forecasting in Small Businesses [1.3750624267664158]
  We study joint 12-month forecasting of 13 income-statement, balance-sheet, cash-flow, and working-capital key performance indicators from 71 monthly ledger series.<n>Across 11,993 forecast origins from 1,060 unseen companies, AGT achieves sample-macro mean absolute error (MAE) $0.6990 pm 0.0013$ over three independent seeds.<n>AGT is best matched on all 13 against LightGBM, TimeMixer, and SOFTS in the seed-42 comparison.
  arXiv  Detail & Related papers  (2026-08-07T09:47:44Z)
• Knowledge Index of Noah's Ark [63.143852586221534]
  We introduce KINA, an 899-item benchmark across 261 fine-grained disciplines.<n>We prove a bonus-on-bar tournament weakly FOSD-dominates flat payment in released-review quality.<n>The top model, Gemini-3.1-Pro-Preview, reaches 53.17%, followed by Claude-Opus-4.6 at 49.92% and GPT-5.4 at 48.55%.
  arXiv  Detail & Related papers  (2026-06-03T17:06:49Z)
• Effective Performance Measurement: Challenges and Opportunities in KPI Extraction from Earnings Calls [43.85438181764358]
  We assess the information captured by models trained on SEC filings and in-context learning methods.<n>We propose a system utilizing LLMs to perform open-ended extraction from unstructured call transcripts.
  arXiv  Detail & Related papers  (2026-05-04T20:40:05Z)
• AgentRaft: Automated Detection of Data Over-Exposure in LLM Agents [40.88941407116349]
  We present AgentRaft, the first automated framework for detecting Data Over-Exposure (DOE) risks in Large Language Model (LLM) agents.<n>We evaluate AgentRaft on a testing environment of 6,675 real-world agent tools.
  arXiv  Detail & Related papers  (2026-03-08T09:40:54Z)
• From Black Box to Glass Box: Cross-Model ASR Disagreement to Prioto Review in Ambient AI Scribe Documentation [43.148402136307716]
  Cross-model disagreement among heterogeneous ASR systems can act as a reference-free uncertainty signal.<n>We transcribed 50 publicly available medical audio clips with eight ASR systems spanning commercial APIs and open-source engines.<n>Low-agreement regions were enriched for content disagreements, with the content fraction increasing from 53.9% to 73.9% across quintiles of high-risk mass.
  arXiv  Detail & Related papers  (2026-03-02T13:02:13Z)
• Coverage-Aware Web Crawling for Domain-Specific Supplier Discovery via a Web--Knowledge--Web Pipeline [0.0]
  Existing business databases suffer from substantial coverage gaps.<n>We propose a textbfWeb--Knowledge--Web (W$to$K$to$W) pipeline.<n>It crawls domain-specific web sources to discover candidate supplier entities.<n>It consolidates structured knowledge into a heterogeneous knowledge graph.
  arXiv  Detail & Related papers  (2026-02-27T18:31:42Z)
• Soft Clustering Anchors for Self-Supervised Speech Representation Learning in Joint Embedding Prediction Architectures [45.74430728311433]
  Joint Embedding Predictive Architectures (JEPA) offer a promising approach to self-supervised speech representation learning, but suffer from representation collapse without explicit grounding.<n>We propose GMM-Anchored JEPA, which fits a Gaussian Mixture Model once on log-mel spectrograms and uses its frozen soft posteriors as auxiliary targets throughout training.<n>On 50k hours of speech, GMM anchoring improves ASR (28.68% vs. 33.22% WER), emotion recognition (67.76% vs. 65.46%), and slot filling (64.7% vs. 59.1% F1) compared to a WavLM-style
  arXiv  Detail & Related papers  (2026-01-30T20:51:37Z)
• FUGC: Benchmarking Semi-Supervised Learning Methods for Cervical Segmentation [63.7829089874007]
  This paper introduces the Fetal Ultrasound Grand Challenge (FUGC), the first benchmark for semi-supervised learning in cervical segmentation.<n>FUGC provides a dataset of 890 TVS images, including 500 training images, 90 validation images, and 300 test images.<n> Methods were evaluated using the Dice Similarity Coefficient (DSC), Hausdorff Distance (HD), and runtime (RT), with a weighted combination of 0.4/0.4/0.2.
  arXiv  Detail & Related papers  (2026-01-22T01:34:39Z)
• SmallML: Bayesian Transfer Learning for Small-Data Predictive Analytics [0.0]
  SmallML achieves enterprise-level prediction accuracy with datasets as small as 50-200 observations.<n> validation on customer churn data demonstrates 96.7% +/- 4.2% AUC with 100 observations per business.<n>By enabling enterprise-grade predictions for 33 million U.S. SMEs, SmallML addresses a critical gap in AI democratization.
  arXiv  Detail & Related papers  (2025-11-18T02:00:55Z)
• Agentic World Modeling for 6G: Near-Real-Time Generative State-Space Reasoning [70.56067503630486]
  We argue that sixth-generation (6G) intelligence is not fluent token prediction but calibrated the capacity to imagine and choose.<n>We show that WM-MS3M cuts mean absolute error (MAE) by 1.69% versus MS3M with 32% fewer parameters and similar latency, and achieves 35-80% lower root mean squared error (RMSE) than attention/hybrid baselines with 2.3-4.1x faster inference.
  arXiv  Detail & Related papers  (2025-11-04T17:22:22Z)
• Shoot First, Ask Questions Later? Building Rational Agents that Explore and Act Like People [81.63702981397408]
  Given limited resources, to what extent do agents based on language models (LMs) act rationally?<n>We develop methods to benchmark and enhance agentic information-seeking, drawing on insights from human behavior.<n>For Spotter agents, our approach boosts accuracy by up to 14.7% absolute over LM-only baselines; for Captain agents, it raises expected information gain (EIG) by up to 0.227 bits (94.2% of the achievable noise ceiling)
  arXiv  Detail & Related papers  (2025-10-23T17:57:28Z)
• Advanced spectral clustering for heterogeneous data in credit risk monitoring systems [8.92280593592798]
  We propose Advanced Spectral Clustering (ASC) to identify meaningful clusters in Heterogeneous Data.<n>By bridging spectral clustering theory with heterogeneous data applications, ASC enables the identification of meaningful clusters, such as recruitment-focused SMEs exhibiting a 30% lower default risk.
  arXiv  Detail & Related papers  (2025-08-30T16:06:00Z)
• Credit Risk Analysis for SMEs Using Graph Neural Networks in Supply Chain [2.060688901523233]
  This paper introduces a Graph Neural Network (GNN)-based framework to map spatial dependencies and predict loan default risks.<n>Tests on real-world datasets from Discover and Ant Credit show the GNN surpasses traditional and other GNN baselines.<n>It also helps regulators model supply chain disruption impacts on banks, accurately forecasting loan defaults from material shortages, and offers Federal Reserve stress testers key data for CCAR risk buffers.
  arXiv  Detail & Related papers  (2025-07-10T15:33:53Z)
• Person Recognition at Altitude and Range: Fusion of Face, Body Shape and Gait [70.00430652562012]
  FarSight is an end-to-end system for person recognition that integrates biometric cues across face, gait, and body shape modalities.<n>FarSight incorporates novel algorithms across four core modules: multi-subject detection and tracking, recognition-aware video restoration, modality-specific biometric feature encoding, and quality-guided multi-modal fusion.
  arXiv  Detail & Related papers  (2025-05-07T17:58:25Z)
• A Cross-Country Analysis of GDPR Cookie Banners and Flexible Methods for Scraping Them [6.533686617147407]
  We examine the top 10,000 websites across 31 countries under the ePrivacy Directive and consent-observatory.eu.<n>We show that 67% of websites use consent interfaces, but only 15% are minimally compliant, mostly because they lack a reject option.<n>There is little evidence that regulators' guidance and fines have impacted compliance rates, but 18% of compliance variance is explained by CMPs.
  arXiv  Detail & Related papers  (2025-03-25T13:44:26Z)
• Heterogeneous Federated Learning via Grouped Sequential-to-Parallel Training [60.892342868936865]
  Federated learning (FL) is a rapidly growing privacy-preserving collaborative machine learning paradigm. We propose a data heterogeneous-robust FL approach, FedGSP, to address this challenge. We show that FedGSP improves the accuracy by 3.7% on average compared with seven state-of-the-art approaches.
  arXiv  Detail & Related papers  (2022-01-31T03:15:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.