Computational Network Design from Functional Specifications

TL;DR

This paper presents an integer programming approach to automatically generate networks from high-level functional specifications, ensuring validity and optimizing design objectives across various applications.

Contribution

It introduces a novel computational method that creates diverse, valid networks solely from high-level specifications, applicable to multiple design domains.

Findings

Successfully generates networks from specifications in street layout, floorplanning, and game design.

Guarantees network validity by fulfilling all hard constraints.

Demonstrates diverse network emergence from high-level functional inputs.

Abstract

Connectivity and layout of underlying networks largely determine the behavior of many environments. For example, transportation networks determine the flow of traffic in cities, or maps determine the difficulty and flow in games. Designing such networks from scratch is challenging as even local network changes can have large global effects. We investigate how to computationally create networks starting from {\em only} high-level functional specifications. Such specifications can be in the form of network density, travel time versus network length, traffic type, destination locations, etc. We propose an integer programming-based approach that guarantees that the resultant networks are valid by fulfilling all specified hard constraints, and score favorably in terms of the objective function. We evaluate our algorithm in three different design settings (i.e., street layout, floorplanning, and game level design) and demonstrate, for the first time, that diverse networks can emerge purely from high-level functional specifications.