arXiv subjects

Yin Yang

Publications and source records attributed to Yin Yang.

At least 145 records · Page 8Linked to original sources

arXiv2021

Lagrangian Coherent Track Initialisation (LCTI)

Advances in time-resolved Particle Tracking Velocimetry (4D-PTV) techniques have been consistently revealed more accurate Lagrangian particle motions. A novel track initialisation technique as a complementary part of 4D-PTV, based on local temporal and spatial coherency of neighbour trajectories, is proposed. The proposed Lagrangian Coherent Track Initialisation (LCTI) applies physics-based Finite Time Lyapunov Exponent (FTLE) to build four frame coherent tracks. We locally determine the boundaries (i.e., ridges) of Lagrangian Coherent Structures (LCS) among neighbour trajectories by using FTLE to distinguish clusters of coherent motions. To evaluate the proposed technique, we created an open-access synthetic Lagrangian and Eulerian dataset of the wake downstream of a smooth cylinder at a Reynolds number equal to 3900 obtained from 3D Direct Numerical Simulation (DNS). The dataset is available to the public. Performance of the proposed method based on three characteristic parameters, temporal scale, particle concentration (i.e., density), and noise ratio, showed robust behaviour in finding true tracks compared to the recent initialisation algorithms. Sensitivity of LCTI to the number of untracked and wrong tracks are also discussed. We address the capability of using the proposed method as a function of a 4D-PTV scheme in the Lagrangian Particle Tracking challenge for a flow with high particle densities. Finally, the LCTI behaviour was assessed in a real jet impingement experiment. LCTI was found to be a reliable tracking tool in complex flow motions, with a strength revealed for flows with high particle concentrations.

physics.flu-dyn↗

arXiv2021

Multi-level Knowledge Distillation via Knowledge Alignment and Correlation

Knowledge distillation (KD) has become an important technique for model compression and knowledge transfer. In this work, we first perform a comprehensive analysis of the knowledge transferred by different KD methods. We demonstrate that traditional KD methods, which minimize the KL divergence of softmax outputs between networks, are related to the knowledge alignment of an individual sample only. Meanwhile, recent contrastive learning-based KD methods mainly transfer relational knowledge between different samples, namely, knowledge correlation. While it is important to transfer the full knowledge from teacher to student, we introduce the Multi-level Knowledge Distillation (MLKD) by effectively considering both knowledge alignment and correlation. MLKD is task-agnostic and model-agnostic, and can easily transfer knowledge from supervised or self-supervised pretrained teachers. We show that MLKD can improve the reliability and transferability of learned representations. Experiments demonstrate that MLKD outperforms other state-of-the-art methods on a large number of experimental settings including different (a) pretraining strategies (b) network architectures (c) datasets (d) tasks.

cs.CV↗

arXiv2021

Compressing Large-Scale Transformer-Based Models: A Case Study on BERT

Pre-trained Transformer-based models have achieved state-of-the-art performance for various Natural Language Processing (NLP) tasks. However, these models often have billions of parameters, and, thus, are too resource-hungry and computation-intensive to suit low-capability devices or applications with strict latency requirements. One potential remedy for this is model compression, which has attracted a lot of research attention. Here, we summarize the research in compressing Transformers, focusing on the especially popular BERT model. In particular, we survey the state of the art in compression for BERT, we clarify the current best practices for compressing large-scale Transformer models, and we provide insights into the workings of various methods. Our categorization and analysis also shed light on promising future research directions for achieving lightweight, accurate, and generic NLP models.

cs.LG↗

arXiv2021

Double cycle-consistent generative adversarial network for unsupervised conditional generation

Conditional generative models have achieved considerable success in the past few years, but usually require a lot of labeled data. Recently, ClusterGAN combines GAN with an encoder to achieve remarkable clustering performance via unsupervised conditional generation. However, it ignores the real conditional distribution of data, which leads to generating less diverse samples for each class and makes the encoder only achieve sub-optimal clustering performance. Here, we propose a new unsupervised conditional generation framework, Double Cycle-Consistent Conditional GAN (DC3-GAN), which can generate diverse class-conditioned samples. We enforce the encoder and the generator of GAN to form an encoder-generator pair in addition to the generator-encoder pair, which enables us to avoid the low-diversity generation and the triviality of latent features. We train the encoder-generator pair using real data, which can indirectly estimate the real conditional distribution. Meanwhile, this framework enforces the outputs of the encoder to match the inputs of GAN and the prior noise distribution, which disentangles latent space into two parts: one-hot discrete and continuous latent variables. The former can be directly expressed as clusters and the latter represents remaining unspecified factors. This work demonstrates that enhancing the diversity of unsupervised conditional generated samples can improve the clustering performance. Experiments on different benchmark datasets show that the proposed method outperforms existing generative model-based clustering methods, and also achieves the optimal disentanglement performance.

cs.LG↗

arXiv2021

In-game Residential Home Planning via Visual Context-aware Global Relation Learning

In this paper, we propose an effective global relation learning algorithm to recommend an appropriate location of a building unit for in-game customization of residential home complex. Given a construction layout, we propose a visual context-aware graph generation network that learns the implicit global relations among the scene components and infers the location of a new building unit. The proposed network takes as input the scene graph and the corresponding top-view depth image. It provides the location recommendations for a newly-added building units by learning an auto-regressive edge distribution conditioned on existing scenes. We also introduce a global graph-image matching loss to enhance the awareness of essential geometry semantics of the site. Qualitative and quantitative experiments demonstrate that the recommended location well reflects the implicit spatial rules of components in the residential estates, and it is instructive and practical to locate the building units in the 3D scene of the complex construction.

cs.CV↗

arXiv2020

Performance Analysis of an Interference-Limited RIS-Aided Network

In this work, the performance of reconfigurable intelligent surface (RIS)-aided communication systems corrupted by the co-channel interference (CCI) at the destination is investigated. Assuming Rayleigh fading and equal-power CCI, we present the analysis for the outage probability (OP), average bit error rate (BER), and ergodic capacity. In addition, an asymptotic outage analysis is carried in order to obtain further insights. Our analysis shows that the number of reflecting elements as well as the number of interferers have a great impact on the overall system performance.

cs.PF↗

arXiv2020

Second-order Neural Network Training Using Complex-step Directional Derivative

While the superior performance of second-order optimization methods such as Newton's method is well known, they are hardly used in practice for deep learning because neither assembling the Hessian matrix nor calculating its inverse is feasible for large-scale problems. Existing second-order methods resort to various diagonal or low-rank approximations of the Hessian, which often fail to capture necessary curvature information to generate a substantial improvement. On the other hand, when training becomes batch-based (i.e., stochastic), noisy second-order information easily contaminates the training procedure unless expensive safeguard is employed. In this paper, we adopt a numerical algorithm for second-order neural network training. We tackle the practical obstacle of Hessian calculation by using the complex-step finite difference (CSFD) -- a numerical procedure adding an imaginary perturbation to the function for derivative computation. CSFD is highly robust, efficient, and accurate (as accurate as the analytic result). This method allows us to literally apply any known second-order optimization methods for deep learning training. Based on it, we design an effective Newton Krylov procedure. The key mechanism is to terminate the stochastic Krylov iteration as soon as a disturbing direction is found so that unnecessary computation can be avoided. During the optimization, we monitor the approximation error in the Taylor expansion to adjust the step size. This strategy combines advantages of line search and trust region methods making our method preserves good local and global convergency at the same time. We have tested our methods in various deep learning tasks. The experiments show that our method outperforms exiting methods, and it often converges one-order faster. We believe our method will inspire a wide-range of new algorithms for deep learning and numerical optimization.

cs.LG↗

arXiv2020

Outage Probability and Capacity Scaling Law of Multiple RIS-Aided Cooperative Networks

In this letter, we consider a dual-hop cooperative network assisted by multiple reconfigurable intelligent surfaces (RISs). Assuming that the RIS with the highest instantaneous end-to-end signal-to-noise ratio (SNR) is selected to aid the communication, the outage probability (OP) and average sum-rate are investigated. Specifically, an exact analysis for the OP is developed. In addition, relying on the extreme value theory, closed-form expressions for the asymptotic OP and asymptotic sum-rate are derived, based on which the capacity scaling law is established. Our results are corroborated through simulations and insightful discussions are provided. In particular, our analysis shows that the number of RISs as well as the number of reflecting elements play a crucial role in the capacity scaling law of multiple RIS-aided cooperative networks. Also, comparisons with relay-aided systems are carried out to demonstrate that the proposed system setup outperforms relaying schemes both in terms of the OP and average sum-rate.

cs.IT↗

arXiv2020

LinSBFT: Linear-Communication One-Step BFT Protocol for Public Blockchains

This paper presents LinSBFT, a Byzantine Fault Tolerance (BFT) protocol with the capacity of processing over 2000 smart contract transactions per second in production. LinSBFT applies to a permissionless, public blockchain system, in which there is no public-key infrastructure, based on the classic PBFT with 4 improvements: (\romannumeral1) LinSBFT achieves $O(n)$ worst-case communication volume, in contract to PBFT's $O(n^4)$; (\romannumeral2) LinSBFT rotates the leader of protocol randomly to reduce the risk of denial-of-service attacks on leader; and (\romannumeral3) each run of LinSBFT finalizes one block, which is robust against participants that are honest in one run of the protocol, and dishonest in another, and the set of participants is dynamic, which is update periodically. (\romannumeral4) LinSBFT helps the delayed nodes to catch up via a synchronization mechanism to promise the liveness. Further, in the ordinary case, LinSBFT involves only a single round of voting instead of two in PBFT, which reduces both communication overhead and confirmation time, and employs the \emph{proof-of-stake} scheme to reward all participants. Extensive experiments using data obtained from the Ethereum demonstrate that LinSBFT consistently and significantly outperforms existing in-production BFT protocols for blockchains.

cs.DC↗

arXiv2020

Homogeneous Network Embedding for Massive Graphs via Reweighted Personalized PageRank

Given an input graph G and a node v in G, homogeneous network embedding (HNE) maps the graph structure in the vicinity of v to a compact, fixed-dimensional feature vector. This paper focuses on HNE for massive graphs, e.g., with billions of edges. On this scale, most existing approaches fail, as they incur either prohibitively high costs, or severely compromised result utility. Our proposed solution, called Node-Reweighted PageRank (NRP), is based on a classic idea of deriving embedding vectors from pairwise personalized PageRank (PPR) values. Our contributions are twofold: first, we design a simple and efficient baseline HNE method based on PPR that is capable of handling billion-edge graphs on commodity hardware; second and more importantly, we identify an inherent drawback of vanilla PPR, and address it in our main proposal NRP. Specifically, PPR was designed for a very different purpose, i.e., ranking nodes in G based on their relative importance from a source node's perspective. In contrast, HNE aims to build node embeddings considering the whole graph. Consequently, node embeddings derived directly from PPR are of suboptimal utility. The proposed NRP approach overcomes the above deficiency through an effective and efficient node reweighting algorithm, which augments PPR values with node degree information, and iteratively adjusts embedding vectors accordingly. Overall, NRP takes O(mlogn) time and O(m) space to compute all node embeddings for a graph with m edges and n nodes. Our extensive experiments that compare NRP against 18 existing solutions over 7 real graphs demonstrate that NRP achieves higher result utility than all the solutions for link prediction, graph reconstruction and node classification, while being up to orders of magnitude faster. In particular, on a billion-edge Twitter graph, NRP terminates within 4 hours, using a single CPU core.

cs.SI↗

arXiv2020

DCAF: A Dynamic Computation Allocation Framework for Online Serving System

Modern large-scale systems such as recommender system and online advertising system are built upon computation-intensive infrastructure. The typical objective in these applications is to maximize the total revenue, e.g. GMV~(Gross Merchandise Volume), under a limited computation resource. Usually, the online serving system follows a multi-stage cascade architecture, which consists of several stages including retrieval, pre-ranking, ranking, etc. These stages usually allocate resource manually with specific computing power budgets, which requires the serving configuration to adapt accordingly. As a result, the existing system easily falls into suboptimal solutions with respect to maximizing the total revenue. The limitation is due to the face that, although the value of traffic requests vary greatly, online serving system still spends equal computing power among them. In this paper, we introduce a novel idea that online serving system could treat each traffic request differently and allocate "personalized" computation resource based on its value. We formulate this resource allocation problem as a knapsack problem and propose a Dynamic Computation Allocation Framework~(DCAF). Under some general assumptions, DCAF can theoretically guarantee that the system can maximize the total revenue within given computation budget. DCAF brings significant improvement and has been deployed in the display advertising system of Taobao for serving the main traffic. With DCAF, we are able to maintain the same business performance with 20\% computation resource reduction.

cs.NI↗

arXiv2020

Realtime Index-Free Single Source SimRank Processing on Web-Scale Graphs

Given a graph G and a node u in G, a single source SimRank query evaluates the similarity between u and every node v in G. Existing approaches to single source SimRank computation incur either long query response time, or expensive pre-computation, which needs to be performed again whenever the graph G changes. Consequently, to our knowledge none of them is ideal for scenarios in which (i) query processing must be done in realtime, and (ii) the underlying graph G is massive, with frequent updates. Motivated by this, we propose SimPush, a novel algorithm that answers single source SimRank queries without any pre-computation, and at the same time achieves significantly higher query processing speed than even the fastest known index-based solutions. Further, SimPush provides rigorous result quality guarantees, and its high performance does not rely on any strong assumption of the underlying graph. Specifically, compared to existing methods, SimPush employs a radically different algorithmic design that focuses on (i) identifying a small number of nodes relevant to the query, and subsequently (ii) computing statistics and performing residue push from these nodes only. We prove the correctness of SimPush, analyze its time complexity, and compare its asymptotic performance with that of existing methods. Meanwhile, we evaluate the practical performance of SimPush through extensive experiments on 8 real datasets. The results demonstrate that SimPush consistently outperforms all existing solutions, often by over an order of magnitude. In particular, on a commodity machine, SimPush answers a single source SimRank query on a web graph containing over 133 million nodes and 5.4 billion edges in under 62 milliseconds, with 0.00035 empirical error, while the fastest index-based competitor needs 1.18 seconds.

cs.DB↗

arXiv2019

DBRec: Dual-Bridging Recommendation via Discovering Latent Groups

In recommender systems, the user-item interaction data is usually sparse and not sufficient for learning comprehensive user/item representations for recommendation. To address this problem, we propose a novel dual-bridging recommendation model (DBRec). DBRec performs latent user/item group discovery simultaneously with collaborative filtering, and interacts group information with users/items for bridging similar users/items. Therefore, a user's preference over an unobserved item, in DBRec, can be bridged by the users within the same group who have rated the item, or the user-rated items that share the same group with the unobserved item. In addition, we propose to jointly learn user-user group (item-item group) hierarchies, so that we can effectively discover latent groups and learn compact user/item representations. We jointly integrate collaborative filtering, latent group discovering and hierarchical modelling into a unified framework, so that all the model parameters can be learned toward the optimization of the objective function. We validate the effectiveness of the proposed model with two real datasets, and demonstrate its advantage over the state-of-the-art recommendation models with extensive experiments.

cs.IR↗

arXiv2019

Efficient Algorithms for Approximate Single-Source Personalized PageRank Queries

Given a graph $G$, a source node $s$ and a target node $t$, the personalized PageRank (PPR) of $t$ with respect to $s$ is the probability that a random walk starting from $s$ terminates at $t$. An important variant of the PPR query is single-source PPR (SSPPR), which enumerates all nodes in $G$, and returns the top-$k$ nodes with the highest PPR values with respect to a given source $s$. PPR in general and SSPPR in particular have important applications in web search and social networks, e.g., in Twitter's Who-To-Follow recommendation service. However, PPR computation is known to be expensive on large graphs, and resistant to indexing. Consequently, previous solutions either use heuristics, which do not guarantee result quality, or rely on the strong computing power of modern data centers, which is costly. Motivated by this, we propose effective index-free and index-based algorithms for approximate PPR processing, with rigorous guarantees on result quality. We first present FORA, an approximate SSPPR solution that combines two existing methods Forward Push (which is fast but does not guarantee quality) and Monte Carlo Random Walk (accurate but slow) in a simple and yet non-trivial way, leading to both high accuracy and efficiency. Further, FORA includes a simple and effective indexing scheme, as well as a module for top-$k$ selection with high pruning power. Extensive experiments demonstrate that the proposed solutions are orders of magnitude more efficient than their respective competitors. Notably, on a billion-edge Twitter dataset, FORA answers a top-500 approximate SSPPR query within 1 second, using a single commodity server.

cs.SI↗

arXiv2019

Computational Design of Skinned Quad-Robots

We present a computational design system that assists users to model, optimize, and fabricate quad-robots with soft skins.Our system addresses the challenging task of predicting their physical behavior by fully integrating the multibody dynamics of the mechanical skeleton and the elastic behavior of the soft skin. The developed motion control strategy uses an alternating optimization scheme to avoid expensive full space time-optimization, interleaving space-time optimization for the skeleton and frame-by-frame optimization for the full dynamics. The output are motor torques to drive the robot to achieve a user prescribed motion trajectory.We also provide a collection of convenient engineering tools and empirical manufacturing guidance to support the fabrication of the designed quad-robot. We validate the feasibility of designs generated with our system through physics simulations and with a physically-fabricated prototype.

cs.GR↗

arXiv2019

Collecting and Analyzing Multidimensional Data with Local Differential Privacy

Local differential privacy (LDP) is a recently proposed privacy standard for collecting and analyzing data, which has been used, e.g., in the Chrome browser, iOS and macOS. In LDP, each user perturbs her information locally, and only sends the randomized version to an aggregator who performs analyses, which protects both the users and the aggregator against private information leaks. Although LDP has attracted much research attention in recent years, the majority of existing work focuses on applying LDP to complex data and/or analysis tasks. In this paper, we point out that the fundamental problem of collecting multidimensional data under LDP has not been addressed sufficiently, and there remains much room for improvement even for basic tasks such as computing the mean value over a single numeric attribute under LDP. Motivated by this, we first propose novel LDP mechanisms for collecting a numeric attribute, whose accuracy is at least no worse (and usually better) than existing solutions in terms of worst-case noise variance. Then, we extend these mechanisms to multidimensional data that can contain both numeric and categorical attributes, where our mechanisms always outperform existing solutions regarding worst-case noise variance. As a case study, we apply our solutions to build an LDP-compliant stochastic gradient descent algorithm (SGD), which powers many important machine learning tasks. Experiments using real datasets confirm the effectiveness of our methods, and their advantages over existing solutions.

cs.CR↗

arXiv2018

LinBFT: Linear-Communication Byzantine Fault Tolerance for Public Blockchains

This paper presents LinBFT, a novel Byzantine fault tolerance (BFT) protocol for blockchain systems that achieves amortized O(n) communication volume per block under reasonable conditions (where n is the number of participants), while satisfying determinist guarantees on safety and liveness. This significantly improves previous results, which either incurs quadratic communication complexity, or only satisfies safety in a probabilistic sense. LinBFT is based on the popular PBFT protocol, and cuts down its $O(n^4)$ complexity with three tricks, each by $O(n)$: linear view change, threshold signatures, and verifiable random functions. All three are known, i.e., the solutions are right in front of our eyes, and yet LinBFT is the first $O(n)$ solution with deterministic security guarantees. Further, LinBFT also addresses issues that are specific to permission-less, public blockchain systems, such as anonymous participants without a public-key infrastructure, proof-of-stake with slashing, rotating leader, and a dynamic participant set. In addition, LinBFT contains no proof-of-work module, reaches consensus for every block, and tolerates changing honesty of the participants for different blocks.

cs.CR↗

arXiv2018

H-CNN: Spatial Hashing Based CNN for 3D Shape Analysis

We present a novel spatial hashing based data structure to facilitate 3D shape analysis using convolutional neural networks (CNNs). Our method well utilizes the sparse occupancy of 3D shape boundary and builds hierarchical hash tables for an input model under different resolutions. Based on this data structure, we design two efficient GPU algorithms namely hash2col and col2hash so that the CNN operations like convolution and pooling can be efficiently parallelized. The spatial hashing is nearly minimal, and our data structure is almost of the same size as the raw input. Compared with state-of-the-art octree-based methods, our data structure significantly reduces the memory footprint during the CNN training. As the input geometry features are more compactly packed, CNN operations also run faster with our data structure. The experiment shows that, under the same network structure, our method yields comparable or better benchmarks compared to the state-of-the-art while it has only one-third memory consumption. Such superior memory performance allows the CNN to handle high-resolution shape analysis.

cs.GR↗