arXiv subjects

Ang Li

Publications and source records attributed to Ang Li.

At least 469 records · Page 26Linked to original sources

arXiv2021

Optimizing FPGA-based Accelerator Design for Large-Scale Molecular Similarity Search

Molecular similarity search has been widely used in drug discovery to identify structurally similar compounds from large molecular databases rapidly. With the increasing size of chemical libraries, there is growing interest in the efficient acceleration of large-scale similarity search. Existing works mainly focus on CPU and GPU to accelerate the computation of the Tanimoto coefficient in measuring the pairwise similarity between different molecular fingerprints. In this paper, we propose and optimize an FPGA-based accelerator design on exhaustive and approximate search algorithms. On exhaustive search using BitBound & folding, we analyze the similarity cutoff and folding level relationship with search speedup and accuracy, and propose a scalable on-the-fly query engine on FPGAs to reduce the resource utilization and pipeline interval. We achieve a 450 million compounds-per-second processing throughput for a single query engine. On approximate search using hierarchical navigable small world (HNSW), a popular algorithm with high recall and query speed. We propose an FPGA-based graph traversal engine to utilize a high throughput register array based priority queue and fine-grained distance calculation engine to increase the processing capability. Experimental results show that the proposed FPGA-based HNSW implementation has a 103385 query per second (QPS) on the Chembl database with 0.92 recall and achieves a 35x speedup than the existing CPU implementation on average. To the best of our knowledge, our FPGA-based implementation is the first attempt to accelerate molecular similarity search algorithms on FPGA and has the highest performance among existing approaches.

cs.AR↗

arXiv2021

ETA Prediction with Graph Neural Networks in Google Maps

Travel-time prediction constitutes a task of high importance in transportation networks, with web mapping services like Google Maps regularly serving vast quantities of travel time queries from users and enterprises alike. Further, such a task requires accounting for complex spatiotemporal interactions (modelling both the topological properties of the road network and anticipating events -- such as rush hours -- that may occur in the future). Hence, it is an ideal target for graph representation learning at scale. Here we present a graph neural network estimator for estimated time of arrival (ETA) which we have deployed in production at Google Maps. While our main architecture consists of standard GNN building blocks, we further detail the usage of training schedule methods such as MetaGradients in order to make our model robust and production-ready. We also provide prescriptive studies: ablating on various architectural decisions and training regimes, and qualitative analyses on real-world situations where our model provides a competitive edge. Our GNN proved powerful when deployed, significantly reducing negative ETA outcomes in several regions compared to the previous production baseline (40+% in cities like Sydney).

cs.LG↗

arXiv2021

A Hybrid System for Learning Classical Data in Quantum States

Deep neural network powered artificial intelligence has rapidly changed our daily life with various applications. However, as one of the essential steps of deep neural networks, training a heavily weighted network requires a tremendous amount of computing resources. Especially in the post-Moore's Law era, the limit of semiconductor fabrication technology has restricted the development of learning algorithms to cope with the increasing high-intensity training data. Meanwhile, quantum computing has demonstrated its significant potential in terms of speeding up the traditionally compute-intensive workloads. For example, Google illustrated quantum supremacy by completing a sampling calculation task in 200 seconds, which is otherwise impracticable on the world's largest supercomputers. To this end, quantum-based learning has become an area of interest, with the potential of a quantum speedup. In this paper, we propose GenQu, a hybrid and general-purpose quantum framework for learning classical data through quantum states. We evaluate GenQu with real datasets and conduct experiments on both simulations and real quantum computer IBM-Q. Our evaluation demonstrates that, compared with classical solutions, the proposed models running on GenQu framework achieve similar accuracy with a much smaller number of qubits, while significantly reducing the parameter size by up to 95.86% and converging speedup by 33.33% faster.

quant-ph↗

arXiv2021

Bayesian inference of quark star equation of state using the NICER PSR J0030+0451 data

We constrain the equation of state of quark stars within the Bayesian statistical approach using the mass and radius measurements of PSR J0030+0451 from NICER. Three types of bag models, with and without non-zero finite quark mass and/or superfluidity, are employed for quark stars made up with self-bound strange quark matter. We find the $90\%$ posterior credible boundary around the most probable values of the quark star maximum mass is $M_{\rm TOV}=2.38_{-0.23}^{+0.26}\,M_{\odot}$, within the model flexibility of the finite quark mass, the quark pairing gap, and the perturbative contribution from the one-gluon exchange. The radius of a canonical $1.4\,M_{\odot}$ quark star is $R_{\rm 1.4}\sim12.3\,{\rm km}$, smaller than the results based on neutron star models.

astro-ph.HE↗

arXiv2021

Bayesian inference of strange star equation of state using the GW170817 and GW190425 data

The observations of compact star inspirals from LIGO/Virgo provide a valuable tool to study the highly uncertain equation of state (EOS) of dense matter at the densities in which the compact stars reside. It is not clear whether the merging stars are neutron stars or quark stars containing self-bound quark matter. In this work, we explore the allowed bag-model-like EOSs by assuming the merging stars are strange quark stars (SQSs) from a Bayesian analysis employing the tidal deformability observational data of the GW170817 and GW190425 binary mergers. We consider two extreme states of strange quark matter, either in nonsuperfluid or color-flavor locked (CFL) and find the results in these two cases essentially reconcile. In particular, our results indicate that the sound speed in the SQS matter is approximately a constant close to the conformal limit of $c/\sqrt{3}$. The universal relations between the mass, the tidal deformability and the compactness are provided for the SQSs. The most probable values of the maximum mass are found to be $M_{\rm TOV}=2.10_{-0.12}^{+0.12}~(2.15_{-0.14}^{+0.16})\,M_{\odot}$ for normal (CFL) SQSs at a $90\%$ confidence level. The corresponding radius and tidal deformability for a $1.4\,M_{\odot}$ star are $R_{\rm 1.4}= 11.50_{-0.55}^{+0.52}~({11.42}_{-0.44}^{+0.52})~\rm km$ and $Λ_{1.4}= {650}_{-190}^{+230}~({630}_{-150}^{+220})$, respectively. We also investigate the possibility of GW190814's secondary component $m_2$ of mass $2.59_{-0.09}^{+0.08}\,M_{\odot}$ being an SQS, and find that it could be a CFL SQS with the pairing gap $Δ$ larger than $244~\rm MeV$ and the effective bag parameter $B_{\rm eff}^{1/4}$ in the range of $170$ to $192$ MeV, at a $90\%$ confidence level.

astro-ph.HE↗

arXiv2021

Binary Complex Neural Network Acceleration on FPGA

Being able to learn from complex data with phase information is imperative for many signal processing applications. Today' s real-valued deep neural networks (DNNs) have shown efficiency in latent information analysis but fall short when applied to the complex domain. Deep complex networks (DCN), in contrast, can learn from complex data, but have high computational costs; therefore, they cannot satisfy the instant decision-making requirements of many deployable systems dealing with short observations or short signal bursts. Recent, Binarized Complex Neural Network (BCNN), which integrates DCNs with binarized neural networks (BNN), shows great potential in classifying complex data in real-time. In this paper, we propose a structural pruning based accelerator of BCNN, which is able to provide more than 5000 frames/s inference throughput on edge devices. The high performance comes from both the algorithm and hardware sides. On the algorithm side, we conduct structural pruning to the original BCNN models and obtain 20 $\times$ pruning rates with negligible accuracy loss; on the hardware side, we propose a novel 2D convolution operation accelerator for the binary complex neural network. Experimental results show that the proposed design works with over 90% utilization and is able to achieve the inference throughput of 5882 frames/s and 4938 frames/s for complex NIN-Net and ResNet-18 using CIFAR-10 dataset and Alveo U280 Board.

cs.LG↗

arXiv2021

Entropic destruction of heavy quarkonium with hyperscaling violation

We study the entropic destruction of heavy quarkonium in strongly coupled theories with an anisotropic scaling symmetry in time and spatial direction. We consider Lifshitz and hyperscaling violation theories which are covariant under a generalized Lifshitz scaling symmetry with the dynamical exponent $z$ and hyperscaling violation exponent $θ$. It is shown that the entropic force depends on the parameters of these theories. In particular, increasing $z$ decreases the entropic force thus reducing the quarkonium dissociation, while increasing $θ$ has opposite effect.

hep-ph↗

arXiv2021

Towards Adversarial Patch Analysis and Certified Defense against Crowd Counting

Crowd counting has drawn much attention due to its importance in safety-critical surveillance systems. Especially, deep neural network (DNN) methods have significantly reduced estimation errors for crowd counting missions. Recent studies have demonstrated that DNNs are vulnerable to adversarial attacks, i.e., normal images with human-imperceptible perturbations could mislead DNNs to make false predictions. In this work, we propose a robust attack strategy called Adversarial Patch Attack with Momentum (APAM) to systematically evaluate the robustness of crowd counting models, where the attacker's goal is to create an adversarial perturbation that severely degrades their performances, thus leading to public safety accidents (e.g., stampede accidents). Especially, the proposed attack leverages the extreme-density background information of input images to generate robust adversarial patches via a series of transformations (e.g., interpolation, rotation, etc.). We observe that by perturbing less than 6\% of image pixels, our attacks severely degrade the performance of crowd counting systems, both digitally and physically. To better enhance the adversarial robustness of crowd counting models, we propose the first regression model-based Randomized Ablation (RA), which is more sufficient than Adversarial Training (ADT) (Mean Absolute Error of RA is 5 lower than ADT on clean samples and 30 lower than ADT on adversarial examples). Extensive experiments on five crowd counting models demonstrate the effectiveness and generality of the proposed method. The supplementary materials and certificate retrained models are available at \url{https://www.dropbox.com/s/hc4fdx133vht0qb/ACM_MM2021_Supp.pdf?dl=0}

cs.CV↗

arXiv2021

On realizations of the subalgebra $A^R(1)$ of the $R$-motivic Steenrod Algebra

In this paper, we show that the finite subalgebra $\mathcal{A}^{\mathbb{R}}(1)$, generated by $\mathrm{Sq}^1$ and $\mathrm{Sq}^2$, of the $\mathbb{R}$-motivic Steenrod algebra $\mathcal{A}^{\mathbb{R}}$ can be given $128$ different $\mathcal{A}^{\mathbb{R}}$-module structures. We also show that all of these $\mathcal{A}^{\mathbb{R}}$-modules can be realized as the cohomology of a $2$-local finite $\mathbb{R}$-motivic spectrum. The realization results are obtained using an $\mathbb{R}$ -motivic analogue of the Toda realization theorem. We notice that each realization of $\mathcal{A}^{\mathbb{R}}(1)$ can be expressed as a cofiber of an $\mathbb{R}$-motivic $v_1$-self-map. The $\mathrm{C}_2$-equivariant analogue of the above results then follows because of the Betti realization functor. We identify a relationship between the $\mathrm{RO}(\mathrm{C}_2)$-graded Steenrod operations on a $\mathrm{C}_2$-equivariant space and the classical Steenrod operations on both its underlying space and its fixed-points. This technique is then used to identify the geometric fixed-point spectra of the $\mathrm{C}_2$-equivariant realizations of $\mathcal{A}^{\mathrm{C}_2}(1)$. We find another application of the $\mathbb{R}$-motivic Toda realization theorem: we produce an $\mathbb{R}$-motivic, and consequently a $\mathrm{C}_2$-equivariant, analogue of the Bhattacharya-Egger spectrum $\mathcal{Z}$, which could be of independent interest.

math.AT↗

arXiv2021

Privacy-Preserving Representation Learning on Graphs: A Mutual Information Perspective

Learning with graphs has attracted significant attention recently. Existing representation learning methods on graphs have achieved state-of-the-art performance on various graph-related tasks such as node classification, link prediction, etc. However, we observe that these methods could leak serious private information. For instance, one can accurately infer the links (or node identity) in a graph from a node classifier (or link predictor) trained on the learnt node representations by existing methods. To address the issue, we propose a privacy-preserving representation learning framework on graphs from the \emph{mutual information} perspective. Specifically, our framework includes a primary learning task and a privacy protection task, and we consider node classification and link prediction as the two tasks of interest. Our goal is to learn node representations such that they can be used to achieve high performance for the primary learning task, while obtaining performance for the privacy protection task close to random guessing. We formally formulate our goal via mutual information objectives. However, it is intractable to compute mutual information in practice. Then, we derive tractable variational bounds for the mutual information terms, where each bound can be parameterized via a neural network. Next, we train these parameterized neural networks to approximate the true mutual information and learn privacy-preserving node representations. We finally evaluate our framework on various graph datasets.

cs.LG↗

arXiv2021

Task-agnostic Continual Learning with Hybrid Probabilistic Models

Learning new tasks continuously without forgetting on a constantly changing data distribution is essential for real-world problems but extremely challenging for modern deep learning. In this work we propose HCL, a Hybrid generative-discriminative approach to Continual Learning for classification. We model the distribution of each task and each class with a normalizing flow. The flow is used to learn the data distribution, perform classification, identify task changes, and avoid forgetting, all leveraging the invertibility and exact likelihood which are uniquely enabled by the normalizing flow model. We use the generative capabilities of the flow to avoid catastrophic forgetting through generative replay and a novel functional regularization technique. For task identification, we use state-of-the-art anomaly detection techniques based on measuring the typicality of the model's statistics. We demonstrate the strong performance of HCL on a range of continual learning benchmarks such as split-MNIST, split-CIFAR, and SVHN-MNIST.

cs.LG↗

arXiv2021

Bounds on Causal Effects and Application to High Dimensional Data

This paper addresses the problem of estimating causal effects when adjustment variables in the back-door or front-door criterion are partially observed. For such scenarios, we derive bounds on the causal effects by solving two non-linear optimization problems, and demonstrate that the bounds are sufficient. Using this optimization method, we propose a framework for dimensionality reduction that allows one to trade bias for estimation power, and demonstrate its performance using simulation studies.

stat.ME↗

arXiv2021

Noise Doesn't Lie: Towards Universal Detection of Deep Inpainting

Deep image inpainting aims to restore damaged or missing regions in an image with realistic contents. While having a wide range of applications such as object removal and image recovery, deep inpainting techniques also have the risk of being manipulated for image forgery. A promising countermeasure against such forgeries is deep inpainting detection, which aims to locate the inpainted regions in an image. In this paper, we make the first attempt towards universal detection of deep inpainting, where the detection network can generalize well when detecting different deep inpainting methods. To this end, we first propose a novel data generation approach to generate a universal training dataset, which imitates the noise discrepancies exist in real versus inpainted image contents to train universal detectors. We then design a Noise-Image Cross-fusion Network (NIX-Net) to effectively exploit the discriminative information contained in both the images and their noise patterns. We empirically show, on multiple benchmark datasets, that our approach outperforms existing detection methods by a large margin and generalize well to unseen deep inpainting techniques. Our universal training dataset can also significantly boost the generalizability of existing detection methods.

cs.CV↗

arXiv2021

Fast and Accurate Single-Image Depth Estimation on Mobile Devices, Mobile AI 2021 Challenge: Report

Depth estimation is an important computer vision problem with many practical applications to mobile devices. While many solutions have been proposed for this task, they are usually very computationally expensive and thus are not applicable for on-device inference. To address this problem, we introduce the first Mobile AI challenge, where the target is to develop an end-to-end deep learning-based depth estimation solutions that can demonstrate a nearly real-time performance on smartphones and IoT platforms. For this, the participants were provided with a new large-scale dataset containing RGB-depth image pairs obtained with a dedicated stereo ZED camera producing high-resolution depth maps for objects located at up to 50 meters. The runtime of all models was evaluated on the popular Raspberry Pi 4 platform with a mobile ARM-based Broadcom chipset. The proposed solutions can generate VGA resolution depth maps at up to 10 FPS on the Raspberry Pi 4 while achieving high fidelity results, and are compatible with any Android or Linux-based mobile devices. A detailed description of all models developed in the challenge is provided in this paper.

eess.IV↗

arXiv2021

PhysGAN: Generating Physical-World-Resilient Adversarial Examples for Autonomous Driving

Although Deep neural networks (DNNs) are being pervasively used in vision-based autonomous driving systems, they are found vulnerable to adversarial attacks where small-magnitude perturbations into the inputs during test time cause dramatic changes to the outputs. While most of the recent attack methods target at digital-world adversarial scenarios, it is unclear how they perform in the physical world, and more importantly, the generated perturbations under such methods would cover a whole driving scene including those fixed background imagery such as the sky, making them inapplicable to physical world implementation. We present PhysGAN, which generates physical-world-resilient adversarial examples for mislead-ing autonomous driving systems in a continuous manner. We show the effectiveness and robustness of PhysGAN via extensive digital and real-world evaluations. Digital experiments show that PhysGAN is effective for various steer-ing models and scenes, which misleads the average steer-ing angle by up to 23.06 degrees under various scenarios. The real-world studies further demonstrate that PhysGAN is sufficiently resilient in practice, which misleads the average steering angle by up to 19.17 degrees. We compare PhysGAN with a set of state-of-the-art baseline methods including several of our self-designed ones, which further demonstrate the robustness and efficacy of our approach. We also show that PhysGAN outperforms state-of-the-art baseline methods To the best of our knowledge, PhysGANis probably the first technique of generating realistic and physical-world-resilient adversarial examples for attacking common autonomous driving scenarios.

cs.CV↗

arXiv2021

DeepObfuscator: Obfuscating Intermediate Representations with Privacy-Preserving Adversarial Learning on Smartphones

Deep learning has been widely applied in many computer vision applications, with remarkable success. However, running deep learning models on mobile devices is generally challenging due to the limitation of computing resources. A popular alternative is to use cloud services to run deep learning models to process raw data. This, however, imposes privacy risks. Some prior arts proposed sending the features extracted from raw data to the cloud. Unfortunately, these extracted features can still be exploited by attackers to recover raw images and to infer embedded private attributes. In this paper, we propose an adversarial training framework, DeepObfuscator, which prevents the usage of the features for reconstruction of the raw images and inference of private attributes. This is done while retaining useful information for the intended cloud service. DeepObfuscator includes a learnable obfuscator that is designed to hide privacy-related sensitive information from the features by performing our proposed adversarial training algorithm. The proposed algorithm is designed by simulating the game between an attacker who makes efforts to reconstruct raw image and infer private attributes from the extracted features and a defender who aims to protect user privacy. By deploying the trained obfuscator on the smartphone, features can be locally extracted and then sent to the cloud. Our experiments on CelebA and LFW datasets show that the quality of the reconstructed images from the obfuscated features of the raw image is dramatically decreased from 0.9458 to 0.3175 in terms of multi-scale structural similarity. The person in the reconstructed image, hence, becomes hardly to be re-identified. The classification accuracy of the inferred private attributes that can be achieved by the attacker is significantly reduced to a random-guessing level.

cs.CR↗

arXiv2021

Causes of Effects: Learning individual responses from population data

The problem of individualization is recognized as crucial in almost every field. Identifying causes of effects in specific events is likewise essential for accurate decision making. However, such estimates invoke counterfactual relationships, and are therefore indeterminable from population data. For example, the probability of benefiting from a treatment concerns an individual having a favorable outcome if treated and an unfavorable outcome if untreated. Experiments conditioning on fine-grained features are fundamentally inadequate because we can't test both possibilities for an individual. Tian and Pearl provided bounds on this and other probabilities of causation using a combination of experimental and observational data. Even though those bounds were proven tight, narrower bounds, sometimes significantly so, can be achieved when structural information is available in the form of a causal model. This has the power to solve central problems, such as explainable AI, legal responsibility, and personalized medicine, all of which demand counterfactual logic. We analyze and expand on existing research by applying bounds to the probability of necessity and sufficiency (PNS) along with graphical criteria and practical applications.

stat.ME↗

arXiv2021

ARENA: Asynchronous Reconfigurable Accelerator Ring to Enable Data-Centric Parallel Computing

The next generation HPC and data centers are likely to be reconfigurable and data-centric due to the trend of hardware specialization and the emergence of data-driven applications. In this paper, we propose ARENA -- an asynchronous reconfigurable accelerator ring architecture as a potential scenario on how the future HPC and data centers will be like. Despite using the coarse-grained reconfigurable arrays (CGRAs) as the substrate platform, our key contribution is not only the CGRA-cluster design itself, but also the ensemble of a new architecture and programming model that enables asynchronous tasking across a cluster of reconfigurable nodes, so as to bring specialized computation to the data rather than the reverse. We presume distributed data storage without asserting any prior knowledge on the data distribution. Hardware specialization occurs at runtime when a task finds the majority of data it requires are available at the present node. In other words, we dynamically generate specialized CGRA accelerators where the data reside. The asynchronous tasking for bringing computation to data is achieved by circulating the task token, which describes the data-flow graphs to be executed for a task, among the CGRA cluster connected by a fast ring network. Evaluations on a set of HPC and data-driven applications across different domains show that ARENA can provide better parallel scalability with reduced data movement (53.9%). Compared with contemporary compute-centric parallel models, ARENA can bring on average 4.37x speedup. The synthesized CGRAs and their task-dispatchers only occupy 2.93mm^2 chip area under 45nm process technology and can run at 800MHz with on average 759.8mW power consumption. ARENA also supports the concurrent execution of multi-applications, offering ideal architectural support for future high-performance parallel computing and data analytics systems.

cs.DC↗