Disentanglement learning aims to separate explanatory factors of variation so that different attributes of the data can be well characterized and isolated, which promotes efficient inference for downstream tasks. Mainstream disentanglement approaches based on generative adversarial networks (GANs) learn interpretable data representation. However, most typical GAN-based works lack the discussion of the latent subspace, causing insufficient consideration of the variation of independent factors. Although some recent research analyzes the latent space on pretrained GANs for image editing, they do not emphasize learning representation directly from the subspace perspective. Appropriate subspace properties could facilitate corresponding feature representation learning to satisfy the independent variation requirements of the obtained explanatory factors, which is crucial for better disentanglement. In this work, we propose a unified framework for ensuring disentanglement, which fully investigates latent subspace learning (SL) in GAN. The novel GAN-based architecture explores orthogonal subspace representation (OSR) on vanilla GAN, named OSRGAN. To guide a subspace with strong correlation, less redundancy, and robust distinguishability, our OSR includes three stages, self-latent-aware, orthogonal subspace-aware, and structure representation-aware, respectively. First, the self-latent-aware stage promotes the latent subspace strongly correlated with the data space to discover interpretable factors, but with poor independence of variation. Second, the following orthogonal subspace-aware stage adaptively learns some 1-D linear subspace spanned by a set of orthogonal bases in the latent space. There is less redundancy between them, expressing the corresponding independence. Third, the structure representation-aware stage aligns the projection on the orthogonal subspace and the latent variables. Accordingly, feature representation in each linear subspace can be distinguishable, enhancing the independent expression of interpretable factors. In addition, we design an alternating optimization step, achieving a tradeoff training of OSRGAN on different properties. Despite it strictly constrains orthogonality, the loss weight coefficient of distinguishability induced by orthogonality could be adjusted and balanced with correlation constraint. To elucidate, this tradeoff training prevents our OSRGAN from overemphasizing any property and damaging the expressiveness of the feature representation. It takes into account both interpretable factors and their independent variation characteristics. Meanwhile, alternating optimization could keep the cost and efficiency of forward inference unchanged and will not burden the computational complexity. In theory, we clarify the significance of OSR, which brings better independence of factors, along with interpretability as correlation could converge to a high range faster. Moreover, through the convergence behavior analysis, including the objective functions under different constraints and the evaluation curve with iterations, our model demonstrates enhanced stability and definitely converges toward a higher peak for disentanglement. To depict the performance in downstream tasks, we compared the state-of-the-art GAN-based and even VAE-based approaches on different datasets. Our OSRGAN achieves higher disentanglement scores on FactorVAE, SAP, MIG, and VP metrics. All the experimental results illustrate that our novel GAN-based framework has considerable advantages on disentanglement.
Advanced microscopy and/or spectroscopy tools play indispensable roles in nanoscience and nanotechnology research, as they provide rich information about material processes and properties. However, the interpretation of imaging data heavily relies on the "intuition" of experienced researchers. As a result, many of the deep graphical features obtained through these tools are often unused because of difficulties in processing the data and finding the correlations. Such challenges can be well addressed by deep learning. In this work, the optical characterization of 2D materials is used as a case study, and a neural-network-based algorithm is demonstrated for the material and thickness identification of 2D materials with high prediction accuracy and real-time processing capability. Further analysis shows that the trained network can extract deep graphical features such as contrast, color, edges, shapes, flake sizes, and their distributions, based on which an ensemble approach is developed to predict the most relevant physical properties of 2D materials. Finally, a transfer learning technique is applied to adapt the pretrained network to other optical identification applications. This artificial-intelligence-based material characterization approach is a powerful tool that would speed up the preparation, initial characterization of 2D materials and other nanomaterials, and potentially accelerate new material discoveries.
The massless Dirac electron transport in graphene has led to a variety of unique light-matter interaction phenomena, which promise many novel optoelectronic applications. Most of the effects are only accessible by breaking the spatial symmetry, through introducing edges, p-n junctions, or heterogeneous interfaces. The recent development of direct synthesis of lateral heterostructures offers new opportunities to achieve the desired asymmetry. As a proof of concept, we study the photothermoelectric effect in an asymmetric lateral heterojunction between the Dirac semimetallic monolayer graphene and the parabolic semiconducting monolayer MoS2. Very different hot-carrier cooling mechanisms on the graphene and the MoS2 sides allow us to resolve the asymmetric thermalization pathways of photoinduced hot carriers spatially with electrostatic gate tunability. We also demonstrate the potential of graphene-2D semiconductor lateral heterojunctions as broadband infrared photodetectors. The proposed structure shows an extreme in-plane asymmetry and provides a new platform to study light-matter interactions in low-dimensional systems.
