Towards Explainable Inverse Design for Photonics via Integrated Gradients

Junho Park, Taehan Kim, Sangdae Nam

Track: Tiny Paper Track (Page limit: 3-5 pages)

Keywords: Inverse Design, Photonic Integrated Circuit, Silicon Photonics, Explainable Model, Integrated Gradients

TL;DR: We aim to make Silicon Photonics design process more explainable/interpretable using Integrated Gradients to highlight the regions positively aligned with the final metrics.

Abstract: Adjoint-based inverse design yields compact, high-performance nanophotonic devices, but the mapping from pixel-level layouts to optical figures of merit remains hard to interpret. We present a simple pipeline that (i) generates a large set of wavelength demultiplexers (WDMs) with SPINS-B, (ii) records each final 2D layout and its spectral metrics (e.g., transmitted power at 1310 nm and 1550 nm), and (iii) trains a lightweight convolutional surrogate to predict these metrics from layouts, enabling (iv) gradient-based attribution via Integrated Gradients (IG) to highlight specific regions most responsible for performance. On a corpus of sampled WDMs, IG saliency consistently localizes to physically meaningful features (e.g., tapers and splitter hubs), offering design intuition that complements adjoint optimization. Our contribution is an end-to-end, data-driven workflow—SPINS-B dataset, CNN surrogate, and IG analysis—that turns inverse-designed layouts into interpretable attributions without modifying the physics solver or objective, and that can be reused for other photonic components.

Submission Number: 6