The performance of surface registration relies heavily on the metric used for the alignment error between the source and target shapes. Traditionally, such a metric is based on the point-to-point or point-to-plane distance from the points on the sour
ce surface to their closest points on the target surface, which is susceptible to failure due to instability of the closest-point correspondence. In this paper, we propose a novel metric based on the intersection points between the two shapes and a random straight line, which does not assume a specific correspondence. We verify the effectiveness of this metric by extensive experiments, including its direct optimization for a single registration problem as well as unsupervised learning for a set of registration problems. The results demonstrate that the algorithms utilizing our proposed metric outperforms the state-of-the-art optimization-based and unsupervised learning-based methods.
Given high-dimensional time series data (e.g., sensor data), how can we detect anomalous events, such as system faults and attacks? More challengingly, how can we do this in a way that captures complex inter-sensor relationships, and detects and expl
ains anomalies which deviate from these relationships? Recently, deep learning approaches have enabled improvements in anomaly detection in high-dimensional datasets; however, existing methods do not explicitly learn the structure of existing relationships between variables, or use them to predict the expected behavior of time series. Our approach combines a structure learning approach with graph neural networks, additionally using attention weights to provide explainability for the detected anomalies. Experiments on two real-world sensor datasets with ground truth anomalies show that our method detects anomalies more accurately than baseline approaches, accurately captures correlations between sensors, and allows users to deduce the root cause of a detected anomaly.
In business domains, textit{bundling} is one of the most important marketing strategies to conduct product promotions, which is commonly used in online e-commerce and offline retailers. Existing recommender systems mostly focus on recommending indivi
dual items that users may be interested in. In this paper, we target at a practical but less explored recommendation problem named bundle recommendation, which aims to offer a combination of items to users. To tackle this specific recommendation problem in the context of the emph{virtual mall} in online games, we formalize it as a link prediction problem on a user-item-bundle tripartite graph constructed from the historical interactions, and solve it with a neural network model that can learn directly on the graph-structure data. Extensive experiments on three public datasets and one industrial game dataset demonstrate the effectiveness of the proposed method. Further, the bundle recommendation model has been deployed in production for more than one year in a popular online game developed by Netease Games, and the launch of the model yields more than 60% improvement on conversion rate of bundles, and a relative improvement of more than 15% on gross merchandise volume (GMV).
In recent years, there are great interests as well as challenges in applying reinforcement learning (RL) to recommendation systems (RS). In this paper, we summarize three key practical challenges of large-scale RL-based recommender systems: massive s
tate and action spaces, high-variance environment, and the unspecific reward setting in recommendation. All these problems remain largely unexplored in the existing literature and make the application of RL challenging. We develop a model-based reinforcement learning framework, called GoalRec. Inspired by the ideas of world model (model-based), value function estimation (model-free), and goal-based RL, a novel disentangled universal value function designed for item recommendation is proposed. It can generalize to various goals that the recommender may have, and disentangle the stochastic environmental dynamics and high-variance reward signals accordingly. As a part of the value function, free from the sparse and high-variance reward signals, a high-capacity reward-independent world model is trained to simulate complex environmental dynamics under a certain goal. Based on the predicted environmental dynamics, the disentangled universal value function is related to the users future trajectory instead of a monolithic state and a scalar reward. We demonstrate the superiority of GoalRec over previous approaches in terms of the above three practical challenges in a series of simulations and a real application.
Electrostatic gating lies in the heart of modern FET-based integrated circuits. Usually, the gate electrode has to be placed very close to the conduction channel, typically a few nanometers, in order to achieve efficient tunability. However, remote c
ontrol of a FET device through a gate electrode placed far away is always highly desired, because it not only reduces the complexity of device fabrication, but also enables designing novel devices with new functionalities. Here, a non-local gating effect in graphene using both near-field optical nano-imaging and electrical transport measurement is reported. With assistance of absorbed water molecules, the charge density of graphene can be efficiently tuned by a local-gate placed over 30 {mu}m away. The observed non-local gating effect is initially driven by an in-plane electric field established between graphene regions with different charge densities due to the quantum capacitance near the Dirac point in graphene. The nonlocality is further amplified and largely enhanced by absorbed water molecules through screening the in-plane electric field and expending the transition length. This research reveals novel non-local phenomenon of Dirac electrons, and paves the way for designing electronic devices with remote-control using 2D materials with small density of states.
The soliton resolution for the Harry Dym equation is established for initial conditions in weighted Sobolev space $H^{1,1}(mathbb{R})$. Combining the nonlinear steepest descent method and $bar{partial}$-derivatives condition, we obtain that when $fra
c{y}{t}<-epsilon(epsilon>0)$ the long time asymptotic expansion of the solution $q(x,t)$ in any fixed cone begin{equation} Cleft(y_{1}, y_{2}, v_{1}, v_{2}right)=left{(y, t) in R^{2} mid y=y_{0}+v t, y_{0} inleft[y_{1}, y_{2}right], v inleft[v_{1}, v_{2}right]right} end{equation} up to an residual error of order $mathcal{O}(t^{-1})$. The expansion shows the long time asymptotic behavior can be described as an $N(I)$-soliton on discrete spectrum whose parameters are modulated by a sum of localized soliton-soliton interactions as one moves through the cone and the second term coming from soliton-radiation interactionson on continuous spectrum.
Late gadolinium enhancement (LGE) cardiac MRI (CMR) is the clinical standard for diagnosis of myocardial scar. 3D isotropic LGE CMR provides improved coverage and resolution compared to 2D imaging. However, image acceleration is required due to long
scan times and contrast washout. Physics-guided deep learning (PG-DL) approaches have recently emerged as an improved accelerated MRI strategy. Training of PG-DL methods is typically performed in supervised manner requiring fully-sampled data as reference, which is challenging in 3D LGE CMR. Recently, a self-supervised learning approach was proposed to enable training PG-DL techniques without fully-sampled data. In this work, we extend this self-supervised learning approach to 3D imaging, while tackling challenges related to small training database sizes of 3D volumes. Results and a reader study on prospectively accelerated 3D LGE show that the proposed approach at 6-fold acceleration outperforms the clinically utilized compressed sensing approach at 3-fold acceleration.
Persistent homology is a method for computing the topological features present in a given data. Recently, there has been much interest in the integration of persistent homology as a computational step in neural networks or deep learning. In order for
a given computation to be integrated in such a way, the computation in question must be differentiable. Computing the gradients of persistent homology is an ill-posed inverse problem with infinitely many solutions. Consequently, it is important to perform regularization so that the solution obtained agrees with known priors. In this work we propose a novel method for regularizing persistent homology gradient computation through the addition of a grouping term. This has the effect of helping to ensure gradients are defined with respect to larger entities and not individual points.
We study the potential of the LHCb 13 TeV single $W^{pm}$ and $Z$ boson pseudo-data for constraining the parton distribution functions (PDFs) of the proton. As an example, we demonstrate the sensitivity of the LHCb 13 TeV data, collected with integra
ted luminosities of 5 fb$^{-1}$ and 300 fb$^{-1}$, to reducing the PDF uncertainty bands of the CT14HERA2 PDFs, using the error PDF updating package {sc ePump}. The sensitivities of various experimental observables are compared. Generally, sizable reductions in PDF uncertainties can be observed in the 300 fb$^{-1}$ data sample, particularly in the small-$x$ region. The double-differential cross section measurement of $Z$ boson $p_T$ and rapidity can greatly reduce the uncertainty bands of $u$ and $d$ quarks in almost the whole $x$ range, as compared to various single observable measurements.
Automated infection measurement and COVID-19 diagnosis based on Chest X-ray (CXR) imaging is important for faster examination. We propose a novel approach, called DRR4Covid, to learn automated COVID-19 diagnosis and infection segmentation on CXRs fro
m digitally reconstructed radiographs (DRRs). DRR4Covid comprises of an infection-aware DRR generator, a classification and/or segmentation network, and a domain adaptation module. The infection-aware DRR generator is able to produce DRRs with adjustable strength of radiological signs of COVID-19 infection, and generate pixel-level infection annotations that match the DRRs precisely. The domain adaptation module is introduced to reduce the domain discrepancy between DRRs and CXRs by training networks on unlabeled real CXRs and labeled DRRs together.We provide a simple but effective implementation of DRR4Covid by using a domain adaptation module based on Maximum Mean Discrepancy (MMD), and a FCN-based network with a classification header and a segmentation header. Extensive experiment results have confirmed the efficacy of our method; specifically, quantifying the performance by accuracy, AUC and F1-score, our network without using any annotations from CXRs has achieved a classification score of (0.954, 0.989, 0.953) and a segmentation score of (0.957, 0.981, 0.956) on a test set with 794 normal cases and 794 positive cases. Besides, we estimate the sensitive of X-ray images in detecting COVID-19 infection by adjusting the strength of radiological signs of COVID-19 infection in synthetic DRRs. The estimated detection limit of the proportion of infected voxels in the lungs is 19.43%, and the estimated lower bound of the contribution rate of infected voxels is 20.0% for significant radiological signs of COVID-19 infection. Our codes will be made publicly available at https://github.com/PengyiZhang/DRR4Covid.
