Sinkhorn-Optimized Capacity-Constrained Temporal Heterogeneous Graph Model for Startup–Investor Matching
- 1School of Journalism, Chongqing University, Chongqing 400044, China
- 2Graduate School of Technology and Management, Kyung Hee University, Seoul 03722, Republic of Korea
Abstract
Investment capacity couples startup–investor recommendations, but independent scoring and ranking ignores this coupling, repeatedly recommending a few investors. We formulate quarterly matching as capacity-constrained entropic optimal transport and propose CapTHG. A relation-specific heterogeneous attention encoder processes causal quarterly snapshots of a temporal heterogeneous graph, and a differentiable Sinkhorn layer converts its scores into a capacity-feasible transport plan. A dustbin handles upper-bound capacities, training is end-to-end with a plan likelihood loss, and an activity-based proxy from a recent window estimates capacity. We characterize the capacity-feasible set with the dustbin score as a retention threshold, derive the linear programming limit and error bound as regularization vanishes, and prove linear convergence and a gradient equal to the plan. In a quarterly rolling evaluation on real financing rounds from a public Crunchbase snapshot, CapTHG attains the highest round-level recall and normalized discounted cumulative gain among all baselines. For every encoder, capacity-constrained Sinkhorn ranking lowers capacity overload and raises investor coverage versus score ranking. Accuracy also improves only under joint training with the plan. Capacity and plan likelihood loss contribute most in the ablation study; results are stable across capacity definitions and candidate sets. Controlled numerical experiments agree with the theory, supporting transport-based capacity-constrained matching.
Related
- The Birkhoff Geometry of Manifold-Constrained Hyper-Connections: Two Channels, Vertex Viscosity, and Sinkhorn as a Retraction
- Capacity Control in a Single-Server Diagnostic--Treatment Queue with Heterogeneous Treatment Modes
- Capacity-Constrained Wasserstein Barycenters: Existence, Duality, and Entropic Regularization
- Constrained Capacity for Faster-than-Nyquist Signaling in Frequency-Selective Fading Channels
- Energy-constrained two-way capacity bounds for noisy Gaussian channels
BibTeX
@article{yang2026sinkhornoptimized,
title = {{Sinkhorn-Optimized Capacity-Constrained Temporal Heterogeneous Graph Model for Startup–Investor Matching}},
author = {Bosen Yang and Chao He},
journal = {Mathematics},
year = {2026},
month = oct,
doi = {10.3390/math14213856},
url = {https://www.mdpi.com/2227-7390/14/21/3856},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Sinkhorn-Optimized Capacity-Constrained Temporal Heterogeneous Graph Model for Startup–Investor Matching
AU - Bosen Yang
AU - Chao He
PY - 2026
DA - 2026/10/22
JO - Mathematics
DO - 10.3390/math14213856
UR - https://www.mdpi.com/2227-7390/14/21/3856
AB - Investment capacity couples startup–investor recommendations, but independent scoring and ranking ignores this coupling, repeatedly recommending a few investors. We formulate quarterly matching as capacity-constrained entropic optimal transport and propose CapTHG. A relation-specific heterogeneous attention encoder processes causal quarterly snapshots of a temporal heterogeneous graph, and a differentiable Sinkhorn layer converts its scores into a capacity-feasible transport plan. A dustbin handles upper-bound capacities, training is end-to-end with a plan likelihood loss, and an activity-based proxy from a recent window estimates capacity. We characterize the capacity-feasible set with the dustbin score as a retention threshold, derive the linear programming limit and error bound as regularization vanishes, and prove linear convergence and a gradient equal to the plan. In a quarterly rolling evaluation on real financing rounds from a public Crunchbase snapshot, CapTHG attains the highest round-level recall and normalized discounted cumulative gain among all baselines. For every encoder, capacity-constrained Sinkhorn ranking lowers capacity overload and raises investor coverage versus score ranking. Accuracy also improves only under joint training with the plan. Capacity and plan likelihood loss contribute most in the ablation study; results are stable across capacity definitions and candidate sets. Controlled numerical experiments agree with the theory, supporting transport-based capacity-constrained matching.
SN - 2227-7390
ER -