Feedforward Ordering in Neural Connectomes via Feedback Arc Minimization

2025/06/13 by Vahidi, Soroush
Computer Science · Neuroscience · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Neural Networks and Applications #Neural dynamics and brain function #Neuroscience and Neural Engineering

paper · pdf · doi:10.48550/arxiv.2506.13799

openalex publication_date 2025/06/13 · openalex created_date 2025/10/18 · openalex updated_date 2026/07/28

Abstract

We present a suite of scalable algorithms for minimizing feedback arcs in large-scale weighted directed graphs, with the goal of revealing biologically meaningful feedforward structure in neural connectomes. Using the FlyWire Connectome Challenge dataset, we demonstrate the effectiveness of our ranking strategies in maximizing the total weight of forward-pointing edges. Our methods integrate greedy heuristics, gain-aware local refinements, and global structural analysis based on strongly connected components. Experiments show that our best solution improves the forward edge weight over previous top-performing methods. All algorithms are implemented efficiently in Python and validated using cloud-based execution on Google Colab Pro+.

Citations

• Minimum Weighted Feedback Arc Sets for Ranking from Pairwise Comparisons
• Flow of Information in Feed-Forward Deep Neural Networks

Related

• 4Ward: a Relayering Strategy for Efficient Training of Arbitrarily Complex Directed Acyclic Graphs
• Optimizing the quantity/quality trade-off in connectome inference
• GraphTreeGen: Subtree-Centric Approach to Efficient and Supervised Graph Generation
• Exploiting Large Neuroimaging Datasets to Create Connectome-Constrained Approaches for more Robust, Efficient, and Adaptable Artificial Intelligence
• SANTIAGO: Spine Association for Neuron Topology Improvement and Graph Optimization