Quantum computing has recently exhibited great potentials in predicting chemical properties for various applications in drug discovery, material design, and catalyst optimization. Progress has been made in simulating small molecules, such as LiH and
hydrogen chains of up to 12 qubits, by using quantum algorithms such as variational quantum eigensolver (VQE). Yet, originating from limitations of the size and the fidelity of near-term quantum hardware, how to accurately simulate large realistic molecules remains a challenge. Here, integrating an adaptive energy sorting strategy and a classical computational method, the density matrix embedding theory, which effectively finds a shallower quantum circuit and reduces the problem size, respectively, we show a means to circumvent the limitations and demonstrate the potential toward solving real chemical problems. We numerically test the method for the hydrogenation reaction of C6H8 and the equilibrium geometry of the C18 molecule, with basis sets up to cc-pVDZ (at most 144 qubits). The simulation results show accuracies comparable to those of advanced quantum chemistry methods such as coupled-cluster or even full configuration interaction, while the number of qubits required is reduced by an order of magnitude (from 144 qubits to 16 qubits for the C18 molecule) compared to conventional VQE. Our work implies the possibility of solving industrial chemical problems on near-term quantum devices.
Image harmonization aims to modify the color of the composited region with respect to the specific background. Previous works model this task as a pixel-wise image-to-image translation using UNet family structures. However, the model size and computa
tional cost limit the performability of their models on edge devices and higher-resolution images. To this end, we propose a novel spatial-separated curve rendering network (S$^2$CRNet) for efficient and high-resolution image harmonization for the first time. In S$^2$CRNet, we firstly extract the spatial-separated embeddings from the thumbnails of the masked foreground and background individually. Then, we design a curve rendering module (CRM), which learns and combines the spatial-specific knowledge using linear layers to generate the parameters of the pixel-wise curve mapping in the foreground region. Finally, we directly render the original high-resolution images using the learned color curve. Besides, we also make two extensions of the proposed framework via the Cascaded-CRM and Semantic-CRM for cascaded refinement and semantic guidance, respectively. Experiments show that the proposed method reduces more than 90% parameters compared with previous methods but still achieves the state-of-the-art performance on both synthesized iHarmony4 and real-world DIH test set. Moreover, our method can work smoothly on higher resolution images in real-time which is more than 10$times$ faster than the existing methods. The code and pre-trained models will be made available and released at https://github.com/stefanLeong/S2CRNet.
Mitotic figure count is an important marker of tumor proliferation and has been shown to be associated with patients prognosis. Deep learning based mitotic figure detection methods have been utilized to automatically locate the cell in mitosis using
hematoxylin & eosin (H&E) stained images. However, the model performance deteriorates due to the large variation of color tone and intensity in H&E images. In this work, we proposed a two stage mitotic figure detection framework by fusing a detector and a deep ensemble classification model. To alleviate the impact of color variation in H&E images, we utilize both stain normalization and data augmentation, aiding model to learn color irrelevant features. The proposed model obtains an F1 score of 0.7550 on the preliminary testing set released by the MIDOG challenge.
We make a systematic study of $Lambda$ hyperon polarizations in unpolarized lepton induced semi-inclusive reactions such as $e^-Nto e^-Lambda X$ and $e^+e^-toLambda h X$. We present the general form of cross sections in terms of structure functions o
btained from a general kinematic analysis. This already shows that the produced hyperons can be polarized in three orthogonal directions, i.e., the longitudinal direction along the hyperon momentum, the normal direction of the production plane, and the transverse direction in the production plane. We present the parton model results at the leading twist and leading order in perturbative QCD and provide the expressions for these structure functions and polarizations in terms of parton distribution functions and fragmentation functions. We emphasize in particular that by studying the longitudinal polarization and the transverse polarization in the production plane, we can extract the corresponding chiral-odd fragmentation functions $H_{1Lq}^{perpLambda}$, $H_{1Tq}^{Lambda}$ and $H_{1Tq}^{perpLambda}$. We also present numerical results of rough estimates utilizing available parameterizations of fragmentation functions and approximations. We discuss how to measure these polarizations and point out in particular that they can be carried out in future EIC and/or $e^+e^-$ annihilation experiments such as Belle.
Recent studies have shown that Graph Convolutional Networks (GCNs) are vulnerable to adversarial attacks on the graph structure. Although multiple works have been proposed to improve their robustness against such structural adversarial attacks, the r
easons for the success of the attacks remain unclear. In this work, we theoretically and empirically demonstrate that structural adversarial examples can be attributed to the non-robust aggregation scheme (i.e., the weighted mean) of GCNs. Specifically, our analysis takes advantage of the breakdown point which can quantitatively measure the robustness of aggregation schemes. The key insight is that weighted mean, as the basic design of GCNs, has a low breakdown point and its output can be dramatically changed by injecting a single edge. We show that adopting the aggregation scheme with a high breakdown point (e.g., median or trimmed mean) could significantly enhance the robustness of GCNs against structural attacks. Extensive experiments on four real-world datasets demonstrate that such a simple but effective method achieves the best robustness performance compared to state-of-the-art models.
Traffic forecasting is a core element of intelligent traffic monitoring system. Approaches based on graph neural networks have been widely used in this task to effectively capture spatial and temporal dependencies of road networks. However, these app
roaches can not effectively define the complicated network topology. Besides, their cascade network structures have limitations in transmitting distinct features in the time and space dimensions. In this paper, we propose a Multi-adaptive Spatiotemporal-flow Graph Neural Network (MAF-GNN) for traffic speed forecasting. MAF-GNN introduces an effective Multi-adaptive Adjacency Matrices Mechanism to capture multiple latent spatial dependencies between traffic nodes. Additionally, we propose Spatiotemporal-flow Modules aiming to further enhance feature propagation in both time and space dimensions. MAF-GNN achieves better performance than other models on two real-world datasets of public traffic network, METR-LA and PeMS-Bay, demonstrating the effectiveness of the proposed approach.
The publics attitudes play a critical role in the acceptance, purchase, use, and research and development of autonomous vehicles (AVs). To date, the publics attitudes towards AVs were mostly estimated through traditional survey data with high labor c
osts and a low quantity of samples, which also might be one of the reasons why the influencing factors on the publics attitudes of AVs have not been studied from multiple aspects in a comprehensive way yet. To address the issue, this study aims to propose a method by using large-scale social media data to investigate key factors that affect the publics attitudes and acceptance of AVs. A total of 954,151 Twitter data related to AVs and 53 candidate independent variables from seven categories were extracted using the web scraping method. Then, sentiment analysis was used to measure the public attitudes towards AVs by calculating sentiment scores. Random forests algorithm was employed to preliminarily select candidate independent variables according to their importance, while a linear mixed model was performed to explore the impacting factors considering the unobserved heterogeneities caused by the subjectivity level of tweets. The results showed that the overall attitude of the public on AVs was slightly optimistic. Factors like drunk, blind spot, and mobility had the largest impacts on public attitudes. In addition, people were more likely to express positive feelings when talking about words such as lidar and Tesla that relate to high technologies. Conversely, factors such as COVID-19, pedestrian, sleepy, and highway were found to have significantly negative effects on the publics attitudes. The findings of this study are beneficial for the development of AV technologies, the guidelines for AV-related policy formulation, and the publics understanding and acceptance of AVs.
Effectively parsing the facade is essential to 3D building reconstruction, which is an important computer vision problem with a large amount of applications in high precision map for navigation, computer aided design, and city generation for digital
entertainments. To this end, the key is how to obtain the shape grammars from 2D images accurately and efficiently. Although enjoying the merits of promising results on the semantic parsing, deep learning methods cannot directly make use of the architectural rules, which play an important role for man-made structures. In this paper, we present a novel translational symmetry-based approach to improving the deep neural networks. Our method employs deep learning models as the base parser, and a module taking advantage of translational symmetry is used to refine the initial parsing results. In contrast to conventional semantic segmentation or bounding box prediction, we propose a novel scheme to fuse segmentation with anchor-free detection in a single stage network, which enables the efficient training and better convergence. After parsing the facades into shape grammars, we employ an off-the-shelf rendering engine like Blender to reconstruct the realistic high-quality 3D models using procedural modeling. We conduct experiments on three public datasets, where our proposed approach outperforms the state-of-the-art methods. In addition, we have illustrated the 3D building models built from 2D facade images.
Vector-based cellular automata (CA) based on real land-parcel has become an important trend in current urban development simulation studies. Compared with raster-based and parcel-based CA models, vector CA models are difficult to be widely used becau
se of their complex data structures and technical difficulties. The UrbanVCA, a brand-new vector CA-based urban development simulation framework was proposed in this study, which supports multiple machine-learning models. To measure the simulation accuracy better, this study also first proposes a vector-based landscape index (VecLI) model based on the real land-parcels. Using Shunde, Guangdong as the study area, the UrbanVCA simulates multiple types of urban land-use changes at the land-parcel level have achieved a high accuracy (FoM=0.243) and the landscape index similarity reaches 87.3%. The simulation results in 2030 show that the eco-protection scenario can promote urban agglomeration and reduce ecological aggression and loss of arable land by at least 60%. Besides, we have developed and released UrbanVCA software for urban planners and researchers.
Despite the recent success of graph neural networks (GNN), common architectures often exhibit significant limitations, including sensitivity to oversmoothing, long-range dependencies, and spurious edges, e.g., as can occur as a result of graph hetero
phily or adversarial attacks. To at least partially address these issues within a simple transparent framework, we consider a new family of GNN layers designed to mimic and integrate the update rules of two classical iterative algorithms, namely, proximal gradient descent and iterative reweighted least squares (IRLS). The former defines an extensible base GNN architecture that is immune to oversmoothing while nonetheless capturing long-range dependencies by allowing arbitrary propagation steps. In contrast, the latter produces a novel attention mechanism that is explicitly anchored to an underlying end-to-end energy function, contributing stability with respect to edge uncertainty. When combined we obtain an extremely simple yet robust model that we evaluate across disparate scenarios including standardized benchmarks, adversarially-perturbated graphs, graphs with heterophily, and graphs involving long-range dependencies. In doing so, we compare against SOTA GNN approaches that have been explicitly designed for the respective task, achieving competitive or superior node classification accuracy. Our code is available at https://github.com/FFTYYY/TWIRLS.
