# OplixNet: Towards Area-Efficient Optical Split-Complex Networks with Real-to-Complex Data Assignment and Knowledge Distillation

arXiv: https://arxiv.org/abs/2312.01403 · HTML: https://mlsanity.com/paper/2312.01403/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Dec 2023.

## Built on by (most cited first, 5 of 5)

- [Basis Sharing: Cross-Layer Parameter Sharing for Large Language Model Compression](https://mlsanity.com/paper/2410.03765/) (2024)
- [Layer-wise dynamic rank for compressing large language models](https://mlsanity.com/paper/2509.25622/) (2025)
- [EncodingNet: A Novel Encoding-based MAC Design for Efficient Neural Network Acceleration](https://mlsanity.com/paper/2402.18595/) (2024)
- [The Impact of Feature Representation on the Accuracy of Photonic Neural Networks](https://mlsanity.com/paper/2406.18757/) (2024)
- [DiffLUT-Net: Differentiable Training of FPGA LUT Networks with Learnable Connectivity](https://mlsanity.com/paper/2609.09254/) (2026)

## Abstract (arXiv)

Having the potential for high speed, high throughput, and low energy cost, optical neural networks (ONNs) have emerged as a promising candidate for accelerating deep learning tasks. In conventional ONNs, light amplitudes are modulated at the input and detected at the output. However, the light phases are still ignored in conventional structures, although they can also carry information for computing. To address this issue, in this paper, we propose a framework called OplixNet to compress the areas of ONNs by modulating input image data into the amplitudes and phase parts of light signals. The input and output parts of the ONNs are redesigned to make full use of both amplitude and phase information. Moreover, mutual learning across different ONN structures is introduced to maintain the accuracy. Experimental results demonstrate that the proposed framework significantly reduces the areas of ONNs with the accuracy within an acceptable range. For instance, 75.03% area is reduced with a 0.33% accuracy decrease on fully connected neural network (FCNN) and 74.88% area is reduced with a 2.38% accuracy decrease on ResNet-32.