arXiv subjects

Li Chen

Publications and source records attributed to Li Chen.

At least 469 records · Page 26Linked to original sources

arXiv2021

P4COM: In-Network Computation with Programmable Switches

Traditionally, switches only provide forwarding services and have no credits on computation in distributed computing frameworks. The emerging programmable switches make in-network computing (INC) possible, i.e., offloading some computation to the switch data plane. While some proposals have attempted to offload computation onto special hardwares (e.g., NetFPGA), many practical issues have not been addressed. Therefore, we propose P4COM - a user-friendly, memory-efficient, and fault-tolerant framework realizing in-network computation (e.g., MapReduce) with programmable switches. P4COM consists of three modules. First, P4COM automatically translates application logic to switch data plane programs with a lightweight interpreter. Second, P4COM adopts a memory management policy to efficiently utilize the limited switch on-chip memory. Third, P4COM provides a cutting-payload mechanism to handle packet losses. We have built a P4COM prototype with a Barefoot Tofino switch and multiple commodity servers. Through a combination of testbed experiments and large-scale simulations, we show that P4COM is able to achieve line-rate processing at 10Gbps links, and can increase the data shuffling throughput by 2-5 times for the MapReduce-style applications.

cs.NI↗

arXiv2021

Controllable Majorana vortex states in iron-based superconducting nanowires

There has been experimental evidence for the Majorana zero modes (MZMs) in solid state systems, which are building blocks for potential topological quantum computing. It is important to design devices, in which MZMs are easy to manipulate and possess a broad topological non-trivial parameter space for fusion and braiding. Here, we propose that the Majorana vortex states in iron-based superconducting nanowires fulfill these desirable conditions. This system has a radius-induced topological phase transition, giving a lower limit to the radius of the nanowire. In the topological phase, there is only one pair of MZMs in the nanowire over a wide range of radius, chemical potential, and external magnetic field. The wavefunction of the MZM has a sizable distribution at the side edge of the nanowire. This property enables one to control the interaction of the MZMs in neighboring vortex nanowires, and paves the way for Majorana fusion and braiding.

cond-mat.supr-con↗

arXiv2021

Joint Echo Cancellation and Noise Suppression based on Cascaded Magnitude and Complex Mask Estimation

Acoustic echo and background noise can seriously degrade the intelligibility of speech. In practice, echo and noise suppression are usually treated as two separated tasks and can be removed with various digital signal processing (DSP) and deep learning techniques. In this paper, we propose a new cascaded model, magnitude and complex temporal convolutional neural network (MC-TCN), to jointly perform acoustic echo cancellation and noise suppression with the help of adaptive filters. The MC-TCN cascades two separation cores, which are used to extract robust magnitude spectra feature and to enhance magnitude and phase simultaneously. Experimental results reveal that the proposed method can achieve superior performance by removing both echo and noise in real-time. In terms of DECMOS, the subjective test shows our method achieves a mean score of 4.41 and outperforms the INTERSPEECH2021 AEC-Challenge baseline by 0.54.

cs.SD↗

arXiv2021

Deep Open Snake Tracker for Vessel Tracing

Vessel tracing by modeling vascular structures in 3D medical images with centerlines and radii can provide useful information for vascular health. Existing algorithms have been developed but there are certain persistent problems such as incomplete or inaccurate vessel tracing, especially in complicated vascular beds like the intracranial arteries. We propose here a deep learning based open curve active contour model (DOST) to trace vessels in 3D images. Initial curves were proposed from a centerline segmentation neural network. Then data-driven machine knowledge was used to predict the stretching direction and vessel radius of the initial curve, while the active contour model (as human knowledge) maintained smoothness and intensity fitness of curves. Finally, considering the nonloop topology of most vasculatures, individually traced vessels were connected into a tree topology by applying a minimum spanning tree algorithm on a global connection graph. We evaluated DOST on a Time-of-Flight (TOF) MRA intracranial artery dataset and demonstrated its superior performance over existing segmentation-based and tracking-based vessel tracing methods. In addition, DOST showed strong adaptability on different imaging modalities (CTA, MR T1 SPACE) and vascular beds (coronary arteries).

eess.IV↗

arXiv2021

Multiplier theorems via martingale transforms

We develop a new approach to prove multiplier theorems in various geometric settings. The main idea is to use martingale transforms and a Gundy-Varopoulos representation for multipliers defined via a suitable extension procedure. Along the way, we provide a probabilistic proof of a generalization of a result by Stinga and Torrea, which is of independent interest. Our methods here also recover the sharp $L^p$ bounds for second order Riesz transforms by a liming argument.

math.PR↗

arXiv2021

The regularity problem for degenerate elliptic operators in weighted spaces

We study the solvability of the regularity problem for degenerate elliptic operators in the block case for data in weighted spaces. More precisely, let $L_w$ be a degenerate elliptic operator with degeneracy given by a fixed weight $w\in A_2(dx)$ in $\mathbb{R}^n$, and consider the associated block second order degenerate elliptic problem in the upper-half space $\mathbb{R}_+^{n+1}$. We obtain non-tangential bounds for the full gradient of the solution of the block case operator given by the Poisson semigroup in terms of the gradient of the boundary data. All this is done in the spaces $L^p(vdw)$ where $v$ is a Muckenhoupt weight with respect to the underlying natural weighted space $(\mathbb{R}^n, wdx)$. We recover earlier results in the non-degenerate case (when $w\equiv 1$, and with or without weight $v$). Our strategy is also different and more direct thanks in particular to recent observations on change of angles in weighted square function estimates and non-tangential maximal functions. Our method gives as a consequence the (unweighted) $L^2(dx)$-solvability of the regularity problem for the block operator \[ \mathbb{L}_αu(x,t) = -|x|^α \mathrm{div}_x \big(|x|^{-α}\,A(x) \nabla_x u(x,t)\big)-\partial_{t}^2 u(x,t) \] for any complex-valued uniformly elliptic matrix $A$ and for all $-ε<α<\frac{2\,n}{n+2}$, where $ε$ depends just on the dimension and the ellipticity constants of $A$.

math.CA↗

arXiv2021

Towards a Better Understanding of Linear Models for Recommendation

Recently, linear regression models, such as EASE and SLIM, have shown to often produce rather competitive results against more sophisticated deep learning models. On the other side, the (weighted) matrix factorization approaches have been popular choices for recommendation in the past and widely adopted in the industry. In this work, we aim to theoretically understand the relationship between these two approaches, which are the cornerstones of model-based recommendations. Through the derivation and analysis of the closed-form solutions for two basic regression and matrix factorization approaches, we found these two approaches are indeed inherently related but also diverge in how they "scale-down" the singular values of the original user-item interaction matrix. This analysis also helps resolve the questions related to the regularization parameter range and model complexities. We further introduce a new learning algorithm in searching (hyper)parameters for the closed-form solution and utilize it to discover the nearby models of the existing solutions. The experimental results demonstrate that the basic models and their closed-form solutions are indeed quite competitive against the state-of-the-art models, thus, confirming the validity of studying the basic models. The effectiveness of exploring the nearby models are also experimentally validated.

cs.IR↗

arXiv2021

Personalized Transformer for Explainable Recommendation

Personalization of natural language generation plays a vital role in a large spectrum of tasks, such as explainable recommendation, review summarization and dialog systems. In these tasks, user and item IDs are important identifiers for personalization. Transformer, which is demonstrated with strong language modeling capability, however, is not personalized and fails to make use of the user and item IDs since the ID tokens are not even in the same semantic space as the words. To address this problem, we present a PErsonalized Transformer for Explainable Recommendation (PETER), on which we design a simple and effective learning objective that utilizes the IDs to predict the words in the target explanation, so as to endow the IDs with linguistic meanings and to achieve personalized Transformer. Besides generating explanations, PETER can also make recommendations, which makes it a unified model for the whole recommendation-explanation pipeline. Extensive experiments show that our small unpretrained model outperforms fine-tuned BERT on the generation task, in terms of both effectiveness and efficiency, which highlights the importance and the nice utility of our design.

cs.IR↗

arXiv2021

$\ell_2$-norm Flow Diffusion in Near-Linear Time

Diffusion is a fundamental graph procedure and has been a basic building block in a wide range of theoretical and empirical applications such as graph partitioning and semi-supervised learning on graphs. In this paper, we study computationally efficient diffusion primitives beyond random walk. We design an $\widetilde{O}(m)$-time randomized algorithm for the $\ell_2$-norm flow diffusion problem, a recently proposed diffusion model based on network flow with demonstrated graph clustering related applications both in theory and in practice. Examples include finding locally-biased low conductance cuts. Using a known connection between the optimal dual solution of the flow diffusion problem and the local cut structure, our algorithm gives an alternative approach for finding such cuts in nearly linear time. From a technical point of view, our algorithm contributes a novel way of dealing with inequality constraints in graph optimization problems. It adapts the high-level algorithmic framework of nearly linear time Laplacian system solvers, but requires several new tools: vertex elimination under constraints, a new family of graph ultra-sparsifiers, and accelerated proximal gradient methods with inexact proximal mapping computation.

cs.DS↗

arXiv2021

Emergent route towards cooperation in interacting games: the dynamical reciprocity

The success of modern civilization is built upon widespread cooperation in human society, deciphering the mechanisms behind has being a major goal for centuries. A crucial fact is, however, largely missing in most prior studies that games in the real world are typically played simultaneously and interactively rather than separately as assumed. Here we introduce the idea of interacting games that different games coevolve and influence each other's decision-making. We show that as the game-game interaction becomes important, the cooperation phase transition dramatically improves, a fairly high level of cooperation is reached for all involved games when interaction goes to be strong. A mean-field theory indicates that a new mechanism -- \emph{the dynamical reciprocity}, as a counterpart to the well-known network reciprocity, is at work to foster cooperation, which is confirmed by the detailed analysis. This revealed reciprocity is robust against variations in the game type, the population structure, and the updating rules etc, and more games generally yield a higher level of cooperation. Our findings point out the great potential towards high cooperation for many issues are interwoven with each other in the real world, and also the possibility of sustaining decent cooperation even in extremely adverse circumstances.

physics.soc-ph↗

arXiv2021

Dynamical reciprocity in interacting games: numerical results and mechanism analysis

We study the evolution of two mutually interacting games with both pairwise games as well as the public goods game on different topologies. On 2d square lattices, we reveal that the game-game interaction can promote the cooperation prevalence in all cases, and the cooperation-defection phase transitions even become absent and fairly high cooperation is expected when the interaction goes to be very strong. A mean-field theory is developed that points out new dynamical routes arising therein. Detailed analysis shows indeed that there are rich categories of interactions in either individual or bulk scenario: invasion, neutral, and catalyzed types; their combination puts cooperators at a persistent advantage position, which boosts the cooperation. The robustness of the revealed reciprocity is strengthened by the studies of model variants, including asymmetrical or time-varying interactions, games of different types, games with time-scale separation, different updating rules etc. The structural complexities of the underlying population, such as Newman--Watts small world networks, Erdős--Rényi random networks, and Barabási--Albert networks, also do not alter the working of the dynamical reciprocity. In particular, as the number of games engaged increases, the cooperation level continuously improves in general. Our work thus uncovers a new class of cooperation mechanism and indicates the great potential for human cooperation where concurrent issues are so often seen in the real world.

physics.soc-ph↗

arXiv2021

A Survey on Conversational Recommender Systems

Recommender systems are software applications that help users to find items of interest in situations of information overload. Current research often assumes a one-shot interaction paradigm, where the users' preferences are estimated based on past observed behavior and where the presentation of a ranked list of suggestions is the main, one-directional form of user interaction. Conversational recommender systems (CRS) take a different approach and support a richer set of interactions. These interactions can, for example, help to improve the preference elicitation process or allow the user to ask questions about the recommendations and to give feedback. The interest in CRS has significantly increased in the past few years. This development is mainly due to the significant progress in the area of natural language processing, the emergence of new voice-controlled home assistants, and the increased use of chatbot technology. With this paper, we provide a detailed survey of existing approaches to conversational recommendation. We categorize these approaches in various dimensions, e.g., in terms of the supported user intents or the knowledge they use in the background. Moreover, we discuss technological approaches, review how CRS are evaluated, and finally identify a number of gaps that deserve more research in the future.

cs.HC↗

arXiv2021

Reversible Adversarial Attack based on Reversible Image Transformation

In order to prevent illegal or unauthorized access of image data such as human faces and ensure legitimate users can use authorization-protected data, reversible adversarial attack technique is rise. Reversible adversarial examples (RAE) get both attack capability and reversibility at the same time. However, the existing technique can not meet application requirements because of serious distortion and failure of image recovery when adversarial perturbations get strong. In this paper, we take advantage of Reversible Image Transformation technique to generate RAE and achieve reversible adversarial attack. Experimental results show that proposed RAE generation scheme can ensure imperceptible image distortion and the original image can be reconstructed error-free. What's more, both the attack ability and the image quality are not limited by the perturbation amplitude.

eess.IV↗

arXiv2021

Switching Transferable Gradient Directions for Query-Efficient Black-Box Adversarial Attacks

We propose a simple and highly query-efficient black-box adversarial attack named SWITCH, which has a state-of-the-art performance in the score-based setting. SWITCH features a highly efficient and effective utilization of the gradient of a surrogate model $\hat{\mathbf{g}}$ w.r.t. the input image, i.e., the transferable gradient. In each iteration, SWITCH first tries to update the current sample along the direction of $\hat{\mathbf{g}}$, but considers switching to its opposite direction $-\hat{\mathbf{g}}$ if our algorithm detects that it does not increase the value of the attack objective function. We justify the choice of switching to the opposite direction by a local approximate linearity assumption. In SWITCH, only one or two queries are needed per iteration, but it is still effective due to the rich information provided by the transferable gradient, thereby resulting in unprecedented query efficiency. To improve the robustness of SWITCH, we further propose SWITCH$_\text{RGF}$ in which the update follows the direction of a random gradient-free (RGF) estimate when neither $\hat{\mathbf{g}}$ nor its opposite direction can increase the objective, while maintaining the advantage of SWITCH in terms of query efficiency. Experimental results conducted on CIFAR-10, CIFAR-100 and TinyImageNet show that compared with other methods, SWITCH achieves a satisfactory attack success rate using much fewer queries, and SWITCH$_\text{RGF}$ achieves the state-of-the-art attack success rate with fewer queries overall. Our approach can serve as a strong baseline for future black-box attacks because of its simplicity. The PyTorch source code is released on https://github.com/machanic/SWITCH.

cs.CV↗

arXiv2021

EXTRA: Explanation Ranking Datasets for Explainable Recommendation

Recently, research on explainable recommender systems has drawn much attention from both academia and industry, resulting in a variety of explainable models. As a consequence, their evaluation approaches vary from model to model, which makes it quite difficult to compare the explainability of different models. To achieve a standard way of evaluating recommendation explanations, we provide three benchmark datasets for EXplanaTion RAnking (denoted as EXTRA), on which explainability can be measured by ranking-oriented metrics. Constructing such datasets, however, poses great challenges. First, user-item-explanation triplet interactions are rare in existing recommender systems, so how to find alternatives becomes a challenge. Our solution is to identify nearly identical sentences from user reviews. This idea then leads to the second challenge, i.e., how to efficiently categorize the sentences in a dataset into different groups, since it has quadratic runtime complexity to estimate the similarity between any two sentences. To mitigate this issue, we provide a more efficient method based on Locality Sensitive Hashing (LSH) that can detect near-duplicates in sub-linear time for a given query. Moreover, we make our code publicly available to allow researchers in the community to create their own datasets.

cs.IR↗

arXiv2021

Cascade Image Matting with Deformable Graph Refinement

Image matting refers to the estimation of the opacity of foreground objects. It requires correct contours and fine details of foreground objects for the matting results. To better accomplish human image matting tasks, we propose the Cascade Image Matting Network with Deformable Graph Refinement, which can automatically predict precise alpha mattes from single human images without any additional inputs. We adopt a network cascade architecture to perform matting from low-to-high resolution, which corresponds to coarse-to-fine optimization. We also introduce the Deformable Graph Refinement (DGR) module based on graph neural networks (GNNs) to overcome the limitations of convolutional neural networks (CNNs). The DGR module can effectively capture long-range relations and obtain more global and local information to help produce finer alpha mattes. We also reduce the computation complexity of the DGR module by dynamically predicting the neighbors and apply DGR module to higher--resolution features. Experimental results demonstrate the ability of our CasDGR to achieve state-of-the-art performance on synthetic datasets and produce good results on real human images.

cs.CV↗

arXiv2021

Improving Robustness for Pose Estimation via Stable Heatmap Regression

Deep learning methods have achieved excellent performance in pose estimation, but the lack of robustness causes the keypoints to change drastically between similar images. In view of this problem, a stable heatmap regression method is proposed to alleviate network vulnerability to small perturbations. We utilize the correlation between different rows and columns in a heatmap to alleviate the multi-peaks problem, and design a highly differentiated heatmap regression to make a keypoint discriminative from surrounding points. A maximum stability training loss is used to simplify the optimization difficulty when minimizing the prediction gap of two similar images. The proposed method achieves a significant advance in robustness over state-of-the-art approaches on two benchmark datasets and maintains high performance.

cs.CV↗

arXiv2021

Hermite Polynomial-based Valuation of American Options with General Jump-Diffusion Processes

We present a new approximation scheme for the price and exercise policy of American options. The scheme is based on Hermite polynomial expansions of the transition density of the underlying asset dynamics and the early exercise premium representation of the American option price. The advantages of the proposed approach are threefold. First, our approach does not require the transition density and characteristic functions of the underlying asset dynamics to be attainable in closed form. Second, our approach is fast and accurate, while the prices and exercise policy can be jointly produced. Third, our approach has a wide range of applications. We show that the proposed approximations of the price and optimal exercise boundary converge to the true ones. We also provide a numerical method based on a step function to implement our proposed approach. Applications to nonlinear mean-reverting models, double mean-reverting models, Merton's and Kou's jump-diffusion models are presented and discussed.

q-fin.CP↗