Papers

Research from TU Delft: decision-focused learning and graph neural networks.

Learning Feasible Decisions Directly from Features for Combinatorial Optimization

Cristian Turcan (first author)

TU Delft Honours Programme · under review at BNAIC 2026

Proposes LR-STE, a solver-free predict-then-optimize method that projects a neural predictor's output onto the problem's linear relaxation and applies a feasibility-correction layer, trained end-to-end with a straight-through estimator to minimise decision regret rather than prediction error. Benchmarked on 0/1 Knapsack and the Travelling Salesperson Problem against SPO+, two-stage predict-then-optimize, and projection-free (STE) baselines.

Heterophilic Methods on Multi-Label Graphs

Cristian Turcan (sole author)

TU Delft Bachelor Research Project (CSE3000) · 2026

Benchmarked 8 models: MLP and DeepWalk baselines plus 6 heterophily GNNs (H2GCN, GPR-GNN, LINKX, FAGCN, ACM-GCN, Ordered GNN), across 5 real and 2 synthetic multi-label graphs in PyTorch Geometric. Controlled homophily and label-cardinality sweeps showed that node-classification performance tracks graph homophily more than model sophistication. Built gnnbench, a config-driven pipeline with a synthetic multi-label graph generator, hardened with split-leakage tests and parallelised as SLURM array jobs on TU Delft's DelftBlue cluster.