arXiv subjects

Ke Chen

Publications and source records attributed to Ke Chen.

At least 271 records · Page 15Linked to original sources

arXiv2020

Catalytically Potent and Selective Clusterzymes for Modulation of Neuroinflammation Through Single-Atom Substitutions

Emerging artificial enzymes with reprogrammed and augmented catalytic activity and substrate selectivity have long been pursued with sustained efforts. The majority of current candidates rely on noble metals or transition metal oxides with rather poor catalytic activity compared with natural molecules. To tackle this limitation, we strategically designed a novel artificial enzyme based on a structurally well-defined Au25 cluster, namely clusterzyme, which is endowed with intrinsic high catalytic activity and selectivity driven by single-atom substitutions with modulated bond lengths. The 3-mercaptopropionic acid (MPA)-stabilized Au24Cu1 and Au24Cd1 clusterzymes exhibit 137 and 160 times higher antioxidant capacities than the natural trolox, respectively. Meanwhile, the clusterzymes each demonstrate preferential enzyme-mimicking catalytic activities with compelling selectivity: Au25 exhibits superior glutathione peroxidase-like (GPx-like) activity; Au24Cu1 shows a distinct advantage towards catalase-like (CAT-like) activity by its Cu single active site; Au24Cd1 preferably acts as a superoxide dismutase-like (SOD-like) enzyme via the Cd single active site. This unique diversified catalytic landscape manifests distinctive reactions against inflammation in brain. Au24Cu1 behaves as an endogenous multi-enzyme mimic that directly decreases peroxide in injured brain via catalytic reactions, while Au24Cd1, catalyzes superoxide and nitrogenous signal molecules by preference, and significantly decreases inflammation factors such as IL-1\b{eta}, IL-6, and TNFα, indicative of an important role in mitigating neuroinflammation.

physics.bio-ph↗

arXiv2020

Geometry-Aware Generation of Adversarial Point Clouds

Machine learning models have been shown to be vulnerable to adversarial examples. While most of the existing methods for adversarial attack and defense work on the 2D image domain, a few recent attempts have been made to extend them to 3D point cloud data. However, adversarial results obtained by these methods typically contain point outliers, which are both noticeable and easy to defend against using the simple techniques of outlier removal. Motivated by the different mechanisms by which humans perceive 2D images and 3D shapes, in this paper we propose the new design of \emph{geometry-aware objectives}, whose solutions favor (the discrete versions of) the desired surface properties of smoothness and fairness. To generate adversarial point clouds, we use a targeted attack misclassification loss that supports continuous pursuit of increasingly malicious signals. Regularizing the targeted attack loss with our proposed geometry-aware objectives results in our proposed method, Geometry-Aware Adversarial Attack ($GeoA^3$). The results of $GeoA^3$ tend to be more harmful, arguably harder to defend against, and of the key adversarial characterization of being imperceptible to humans. While the main focus of this paper is to learn to generate adversarial point clouds, we also present a simple but effective algorithm termed $Geo_{+}A^3$-IterNormPro, with Iterative Normal Projection (IterNorPro) that solves a new objective function $Geo_{+}A^3$, towards surface-level adversarial attacks via generation of adversarial point clouds. We quantitatively evaluate our methods on both synthetic and physical objects in terms of attack success rate and geometric regularity. For a qualitative evaluation, we conduct subjective studies by collecting human preferences from Amazon Mechanical Turk. Comparative results in comprehensive experiments confirm the advantages of our proposed methods.

cs.CV↗

arXiv2020

LINDT: Tackling Negative Federated Learning with Local Adaptation

Federated Learning (FL) is a promising distributed learning paradigm, which allows a number of data owners (also called clients) to collaboratively learn a shared model without disclosing each client's data. However, FL may fail to proceed properly, amid a state that we call negative federated learning (NFL). This paper addresses the problem of negative federated learning. We formulate a rigorous definition of NFL and analyze its essential cause. We propose a novel framework called LINDT for tackling NFL in run-time. The framework can potentially work with any neural-network-based FL systems for NFL detection and recovery. Specifically, we introduce a metric for detecting NFL from the server. On occasion of NFL recovery, the framework makes adaptation to the federated model on each client's local data by learning a Layer-wise Intertwined Dual-model. Experiment results show that the proposed approach can significantly improve the performance of FL on local data in various scenarios of NFL.

cs.LG↗

arXiv2020

Learning Audio Embeddings with User Listening Data for Content-based Music Recommendation

Personalized recommendation on new track releases has always been a challenging problem in the music industry. To combat this problem, we first explore user listening history and demographics to construct a user embedding representing the user's music preference. With the user embedding and audio data from user's liked and disliked tracks, an audio embedding can be obtained for each track using metric learning with Siamese networks. For a new track, we can decide the best group of users to recommend by computing the similarity between the track's audio embedding and different user embeddings, respectively. The proposed system yields state-of-the-art performance on content-based music recommendation tested with millions of users and tracks. Also, we extract audio embeddings as features for music genre classification tasks. The results show the generalization ability of our audio embeddings.

cs.SD↗

arXiv2020

Molten salt synthesis of a nanolaminated Sc2SnC MAX Phase

The MAX phases are a family of of ternary layered material with both metal and ceramic properties, and it is also precursor ma-terials for synthesis of two-dimensional MXenes. The theory predicted that there are more than 600 stable ternary layered MAX phases. At present, there are more than 80 kinds of ternary MAX phases synthesized through experiments, and few reports on MAX phases where M is a rare earth element. In this study, a new MAX phase Sc2SnC with rare earth element Sc at the M sites was synthesized through the reaction sintering of Sc, Sn, and C mixtures. Phase composition and microstructure of Sc2SnC were confirmed by X-ray diffraction, scanning electron microscopy and X-ray energy spectrum analysis. And structural stability, mechanical and electronic properties of Sc2SnC was investigated via density functional theory. This study open a door for ex-plore more unknown ternary layered rare earth compounds Ren+1SnCn (Re=Sc, Y, La-Nd, n=1) and corresponding rare earth MXenes.

cond-mat.mtrl-sci↗

arXiv2020

Feature Importance Ranking for Deep Learning

Feature importance ranking has become a powerful tool for explainable AI. However, its nature of combinatorial optimization poses a great challenge for deep learning. In this paper, we propose a novel dual-net architecture consisting of operator and selector for discovery of an optimal feature subset of a fixed size and ranking the importance of those features in the optimal subset simultaneously. During learning, the operator is trained for a supervised learning task via optimal feature subset candidates generated by the selector that learns predicting the learning performance of the operator working on different optimal subset candidates. We develop an alternate learning algorithm that trains two nets jointly and incorporates a stochastic local search procedure into learning to address the combinatorial optimization challenge. In deployment, the selector generates an optimal feature subset and ranks feature importance, while the operator makes predictions based on the optimal subset for test data. A thorough evaluation on synthetic, benchmark and real data sets suggests that our approach outperforms several state-of-the-art feature importance ranking and supervised feature selection methods. (Our source code is available: https://github.com/maksym33/FeatureImportanceDL)

cs.LG↗

arXiv2020

Compositional Few-Shot Recognition with Primitive Discovery and Enhancing

Few-shot learning (FSL) aims at recognizing novel classes given only few training samples, which still remains a great challenge for deep learning. However, humans can easily recognize novel classes with only few samples. A key component of such ability is the compositional recognition that human can perform, which has been well studied in cognitive science but is not well explored in FSL. Inspired by such capability of humans, to imitate humans' ability of learning visual primitives and composing primitives to recognize novel classes, we propose an approach to FSL to learn a feature representation composed of important primitives, which is jointly trained with two parts, i.e. primitive discovery and primitive enhancing. In primitive discovery, we focus on learning primitives related to object parts by self-supervision from the order of image splits, avoiding extra laborious annotations and alleviating the effect of semantic gaps. In primitive enhancing, inspired by current studies on the interpretability of deep networks, we provide our composition view for the FSL baseline model. To modify this model for effective composition, inspired by both mathematical deduction and biological studies (the Hebbian Learning rule and the Winner-Take-All mechanism), we propose a soft composition mechanism by enlarging the activation of important primitives while reducing that of others, so as to enhance the influence of important primitives and better utilize these primitives to compose novel classes. Extensive experiments on public benchmarks are conducted on both the few-shot image classification and video recognition tasks. Our method achieves the state-of-the-art performance on all these datasets and shows better interpretability.

cs.CV↗

arXiv2020

Improving Semantic Analysis on Point Clouds via Auxiliary Supervision of Local Geometric Priors

Existing deep learning algorithms for point cloud analysis mainly concern discovering semantic patterns from global configuration of local geometries in a supervised learning manner. However, very few explore geometric properties revealing local surface manifolds embedded in 3D Euclidean space to discriminate semantic classes or object parts as additional supervision signals. This paper is the first attempt to propose a unique multi-task geometric learning network to improve semantic analysis by auxiliary geometric learning with local shape properties, which can be either generated via physical computation from point clouds themselves as self-supervision signals or provided as privileged information. Owing to explicitly encoding local shape manifolds in favor of semantic analysis, the proposed geometric self-supervised and privileged learning algorithms can achieve superior performance to their backbone baselines and other state-of-the-art methods, which are verified in the experiments on the popular benchmarks.

cs.CV↗

arXiv2020

CAD-PU: A Curvature-Adaptive Deep Learning Solution for Point Set Upsampling

Point set is arguably the most direct approximation of an object or scene surface, yet its practical acquisition often suffers from the shortcoming of being noisy, sparse, and possibly incomplete, which restricts its use for a high-quality surface recovery. Point set upsampling aims to increase its density and regularity such that a better surface recovery could be achieved. The problem is severely ill-posed and challenging, considering that the upsampling target itself is only an approximation of the underlying surface. Motivated to improve the surface approximation via point set upsampling, we identify the factors that are critical to the objective, by pairing the surface approximation error bounds of the input and output point sets. It suggests that given a fixed budget of points in the upsampling result, more points should be distributed onto the surface regions where local curvatures are relatively high. To implement the motivation, we propose a novel design of Curvature-ADaptive Point set Upsampling network (CAD-PU), the core of which is a module of curvature-adaptive feature expansion. To train CAD-PU, we follow the same motivation and propose geometrically intuitive surrogates that approximate discrete notions of surface curvature for the upsampled point set. We further integrate the proposed surrogates into an adversarial learning based curvature minimization objective, which gives a practically effective learning of CAD-PU. We conduct thorough experiments that show the efficacy of our contributions and the advantages of our method over existing ones. Our implementation codes are publicly available at https://github.com/JiehongLin/CAD-PU.

cs.CV↗

arXiv2020

MVLidarNet: Real-Time Multi-Class Scene Understanding for Autonomous Driving Using Multiple Views

Autonomous driving requires the inference of actionable information such as detecting and classifying objects, and determining the drivable space. To this end, we present Multi-View LidarNet (MVLidarNet), a two-stage deep neural network for multi-class object detection and drivable space segmentation using multiple views of a single LiDAR point cloud. The first stage processes the point cloud projected onto a perspective view in order to semantically segment the scene. The second stage then processes the point cloud (along with semantic labels from the first stage) projected onto a bird's eye view, to detect and classify objects. Both stages use an encoder-decoder architecture. We show that our multi-view, multi-stage, multi-class approach is able to detect and classify objects while simultaneously determining the drivable space using a single LiDAR scan as input, in challenging scenes with more than one hundred vehicles and pedestrians at a time. The system operates efficiently at 150 fps on an embedded GPU designed for a self-driving car, including a postprocessing step to maintain identities over time. We show results on both KITTI and a much larger internal dataset, thus demonstrating the method's ability to scale by an order of magnitude.

cs.CV↗

arXiv2020

POP909: A Pop-song Dataset for Music Arrangement Generation

Music arrangement generation is a subtask of automatic music generation, which involves reconstructing and re-conceptualizing a piece with new compositional techniques. Such a generation process inevitably requires reference from the original melody, chord progression, or other structural information. Despite some promising models for arrangement, they lack more refined data to achieve better evaluations and more practical results. In this paper, we propose POP909, a dataset which contains multiple versions of the piano arrangements of 909 popular songs created by professional musicians. The main body of the dataset contains the vocal melody, the lead instrument melody, and the piano accompaniment for each song in MIDI format, which are aligned to the original audio files. Furthermore, we provide the annotations of tempo, beat, key, and chords, where the tempo curves are hand-labeled and others are done by MIR algorithms. Finally, we conduct several baseline experiments with this dataset using standard deep music generation algorithms.

cs.SD↗

arXiv2020

MusPy: A Toolkit for Symbolic Music Generation

In this paper, we present MusPy, an open source Python library for symbolic music generation. MusPy provides easy-to-use tools for essential components in a music generation system, including dataset management, data I/O, data preprocessing and model evaluation. In order to showcase its potential, we present statistical analysis of the eleven datasets currently supported by MusPy. Moreover, we conduct a cross-dataset generalizability experiment by training an autoregressive model on each dataset and measuring held-out likelihood on the others---a process which is made easier by MusPy's dataset management system. The results provide a map of domain overlap between various commonly used datasets and show that some datasets contain more representative cross-genre samples than others. Along with the dataset analysis, these results might serve as a guide for choosing datasets in future research. Source code and documentation are available at https://github.com/salu133445/muspy .

cs.SD↗

arXiv2020

Music SketchNet: Controllable Music Generation via Factorized Representations of Pitch and Rhythm

Drawing an analogy with automatic image completion systems, we propose Music SketchNet, a neural network framework that allows users to specify partial musical ideas guiding automatic music generation. We focus on generating the missing measures in incomplete monophonic musical pieces, conditioned on surrounding context, and optionally guided by user-specified pitch and rhythm snippets. First, we introduce SketchVAE, a novel variational autoencoder that explicitly factorizes rhythm and pitch contour to form the basis of our proposed model. Then we introduce two discriminative architectures, SketchInpainter and SketchConnector, that in conjunction perform the guided music completion, filling in representations for the missing measures conditioned on surrounding context and user-specified snippets. We evaluate SketchNet on a standard dataset of Irish folk music and compare with models from recent works. When used for music completion, our approach outperforms the state-of-the-art both in terms of objective metrics and subjective listening tests. Finally, we demonstrate that our model can successfully incorporate user-specified snippets during the generation process.

cs.LG↗

arXiv2020

A low-rank Schwarz method for radiative transport equation with heterogeneous scattering coefficient

Random sampling has been used to find low-rank structure and to build fast direct solvers for multiscale partial differential equations of various types. In this work, we design an accelerated Schwarz method for radiative transfer equations that makes use of approximate local solution maps constructed offline via a random sampling strategy. Numerical examples demonstrate the accuracy, robustness, and efficiency of the proposed approach.

math.NA↗

arXiv2020

Structured random sketching for PDE inverse problems

For an overdetermined system $\mathsf{A}\mathsf{x} \approx \mathsf{b}$ with $\mathsf{A}$ and $\mathsf{b}$ given, the least-square (LS) formulation $\min_x \, \|\mathsf{A}\mathsf{x}-\mathsf{b}\|_2$ is often used to find an acceptable solution $\mathsf{x}$. The cost of solving this problem depends on the dimensions of $\mathsf{A}$, which are large in many practical instances. This cost can be reduced by the use of random sketching, in which we choose a matrix $\mathsf{S}$ with fewer rows than $\mathsf{A}$ and $\mathsf{b}$, and solve the sketched LS problem $\min_x \, \|\mathsf{S}(\mathsf{A} \mathsf{x}-\mathsf{b})\|_2$ to obtain an approximate solution to the original LS problem. Significant theoretical and practical progress has been made in the last decade in designing the appropriate structure and distribution for the sketching matrix $\mathsf{S}$. When $\mathsf{A}$ and $\mathsf{b}$ arise from discretizations of a PDE-based inverse problem, tensor structure is often present in $\mathsf{A}$ and $\mathsf{b}$. For reasons of practical efficiency, $\mathsf{S}$ should be designed to have a structure consistent with that of $\mathsf{A}$. Can we claim similar approximation properties for the solution of the sketched LS problem with structured $\mathsf{S}$ as for fully-random $\mathsf{S}$? We give estimates that relate the quality of the solution of the sketched LS problem to the size of the structured sketching matrices, for two different structures. Our results are among the first known for random sketching matrices whose structure is suitable for use in PDE inverse problems.

math.NA↗

arXiv2020

On the Longest Spanning Tree with Neighborhoods

We study a maximization problem for geometric network design. Given a set of $n$ compact neighborhoods in $\mathbb{R}^d$, select a point in each neighborhood, so that the longest spanning tree on these points (as vertices) has maximum length. Here we give an approximation algorithm with ratio $0.511$, which represents the first, albeit small, improvement beyond $1/2$. While we suspect that the problem is NP-hard already in the plane, this issue remains open.

cs.CG↗

arXiv2020

Efficient Feature-based Image Registration by Mapping Sparsified Surfaces

With the advancement in the digital camera technology, the use of high resolution images and videos has been widespread in the modern society. In particular, image and video frame registration is frequently applied in computer graphics and film production. However, conventional registration approaches usually require long computational time for high resolution images and video frames. This hinders the application of the registration approaches in the modern industries. In this work, we first propose a new image representation method to accelerate the registration process by triangulating the images effectively. For each high resolution image or video frame, we compute an optimal coarse triangulation which captures the important features of the image. Then, we apply a surface registration algorithm to obtain a registration map which is used to compute the registration of the high resolution image. Experimental results suggest that our overall algorithm is efficient and capable to achieve a high compression rate while the accuracy of the registration is well retained when compared with the conventional grid-based approach. Also, the computational time of the registration is significantly reduced using our triangulation-based approach.

cs.GR↗

arXiv2020

Multiparty Selection

Given a sequence $A$ of $n$ numbers and an integer (target) parameter $1\leq i\leq n$, the (exact) selection problem asks to find the $i$-th smallest element in $A$. An element is said to be $(i,j)$-mediocre if it is neither among the top $i$ nor among the bottom $j$ elements of $S$. The approximate selection problem asks to find a $(i,j)$-mediocre element for some given $i,j$; as such, this variant allows the algorithm to return any element in a prescribed range. In the first part, we revisit the selection problem in the two-party model introduced by Andrew Yao (1979) and then extend our study of exact selection to the multiparty model. In the second part, we deduce some communication complexity benefits that arise in approximate selection. In particular, we present a deterministic protocol for finding an approximate median among $k$ players.

cs.DS↗