arXiv subjects

Jian Tang

Publications and source records attributed to Jian Tang.

At least 289 records · Page 16Linked to original sources

arXiv2020

Fast Object Detection with Latticed Multi-Scale Feature Fusion

Scale variance is one of the crucial challenges in multi-scale object detection. Early approaches address this problem by exploiting the image and feature pyramid, which raises suboptimal results with computation burden and constrains from inherent network structures. Pioneering works also propose multi-scale (i.e., multi-level and multi-branch) feature fusions to remedy the issue and have achieved encouraging progress. However, existing fusions still have certain limitations such as feature scale inconsistency, ignorance of level-wise semantic transformation, and coarse granularity. In this work, we present a novel module, the Fluff block, to alleviate drawbacks of current multi-scale fusion methods and facilitate multi-scale object detection. Specifically, Fluff leverages both multi-level and multi-branch schemes with dilated convolutions to have rapid, effective and finer-grained feature fusions. Furthermore, we integrate Fluff to SSD as FluffNet, a powerful real-time single-stage detector for multi-scale object detection. Empirical results on MS COCO and PASCAL VOC have demonstrated that FluffNet obtains remarkable efficiency with state-of-the-art accuracy. Additionally, we indicate the great generality of the Fluff block by showing how to embed it to other widely-used detectors as well.

cs.CV↗

arXiv2020

COVI-AgentSim: an Agent-based Model for Evaluating Methods of Digital Contact Tracing

The rapid global spread of COVID-19 has led to an unprecedented demand for effective methods to mitigate the spread of the disease, and various digital contact tracing (DCT) methods have emerged as a component of the solution. In order to make informed public health choices, there is a need for tools which allow evaluation and comparison of DCT methods. We introduce an agent-based compartmental simulator we call COVI-AgentSim, integrating detailed consideration of virology, disease progression, social contact networks, and mobility patterns, based on parameters derived from empirical research. We verify by comparing to real data that COVI-AgentSim is able to reproduce realistic COVID-19 spread dynamics, and perform a sensitivity analysis to verify that the relative performance of contact tracing methods are consistent across a range of settings. We use COVI-AgentSim to perform cost-benefit analyses comparing no DCT to: 1) standard binary contact tracing (BCT) that assigns binary recommendations based on binary test results; and 2) a rule-based method for feature-based contact tracing (FCT) that assigns a graded level of recommendation based on diverse individual features. We find all DCT methods consistently reduce the spread of the disease, and that the advantage of FCT over BCT is maintained over a wide range of adoption rates. Feature-based methods of contact tracing avert more disability-adjusted life years (DALYs) per socioeconomic cost (measured by productive hours lost). Our results suggest any DCT method can help save lives, support re-opening of economies, and prevent second-wave outbreaks, and that FCT methods are a promising direction for enriching BCT using self-reported symptoms, yielding earlier warning signals and a significantly reduced spread of the virus per socioeconomic cost.

cs.CY↗

arXiv2020

$P^2$ Net: Augmented Parallel-Pyramid Net for Attention Guided Pose Estimation

We propose an augmented Parallel-Pyramid Net ($P^2~Net$) with feature refinement by dilated bottleneck and attention module. During data preprocessing, we proposed a differentiable auto data augmentation ($DA^2$) method. We formulate the problem of searching data augmentaion policy in a differentiable form, so that the optimal policy setting can be easily updated by back propagation during training. $DA^2$ improves the training efficiency. A parallel-pyramid structure is followed to compensate the information loss introduced by the network. We innovate two fusion structures, i.e. Parallel Fusion and Progressive Fusion, to process pyramid features from backbone network. Both fusion structures leverage the advantages of spatial information affluence at high resolution and semantic comprehension at low resolution effectively. We propose a refinement stage for the pyramid features to further boost the accuracy of our network. By introducing dilated bottleneck and attention module, we increase the receptive field for the features with limited complexity and tune the importance to different feature channels. To further refine the feature maps after completion of feature extraction stage, an Attention Module ($AM$) is defined to extract weighted features from different scale feature maps generated by the parallel-pyramid structure. Compared with the traditional up-sampling refining, $AM$ can better capture the relationship between channels. Experiments corroborate the effectiveness of our proposed method. Notably, our method achieves the best performance on the challenging MSCOCO and MPII datasets.

cs.CV↗

arXiv2020

Graph Policy Network for Transferable Active Learning on Graphs

Graph neural networks (GNNs) have been attracting increasing popularity due to their simplicity and effectiveness in a variety of fields. However, a large number of labeled data is generally required to train these networks, which could be very expensive to obtain in some domains. In this paper, we study active learning for GNNs, i.e., how to efficiently label the nodes on a graph to reduce the annotation cost of training GNNs. We formulate the problem as a sequential decision process on graphs and train a GNN-based policy network with reinforcement learning to learn the optimal query strategy. By jointly training on several source graphs with full labels, we learn a transferable active learning policy which can directly generalize to unlabeled target graphs. Experimental results on multiple datasets from different domains prove the effectiveness of the learned policy in promoting active learning performance in both settings of transferring between graphs in the same domain and across different domains.

cs.LG↗

arXiv2020

Predicting Infectiousness for Proactive Contact Tracing

The COVID-19 pandemic has spread rapidly worldwide, overwhelming manual contact tracing in many countries and resulting in widespread lockdowns for emergency containment. Large-scale digital contact tracing (DCT) has emerged as a potential solution to resume economic and social activity while minimizing spread of the virus. Various DCT methods have been proposed, each making trade-offs between privacy, mobility restrictions, and public health. The most common approach, binary contact tracing (BCT), models infection as a binary event, informed only by an individual's test results, with corresponding binary recommendations that either all or none of the individual's contacts quarantine. BCT ignores the inherent uncertainty in contacts and the infection process, which could be used to tailor messaging to high-risk individuals, and prompt proactive testing or earlier warnings. It also does not make use of observations such as symptoms or pre-existing medical conditions, which could be used to make more accurate infectiousness predictions. In this paper, we use a recently-proposed COVID-19 epidemiological simulator to develop and test methods that can be deployed to a smartphone to locally and proactively predict an individual's infectiousness (risk of infecting others) based on their contact history and other information, while respecting strong privacy constraints. Predictions are used to provide personalized recommendations to the individual via an app, as well as to send anonymized messages to the individual's contacts, who use this information to better predict their own infectiousness, an approach we call proactive contact tracing (PCT). We find a deep-learning based PCT method which improves over BCT for equivalent average mobility, suggesting PCT could help in safe re-opening and second-wave prevention.

cs.LG↗

arXiv2020

Knowledge Transfer in Multi-Task Deep Reinforcement Learning for Continuous Control

While Deep Reinforcement Learning (DRL) has emerged as a promising approach to many complex tasks, it remains challenging to train a single DRL agent that is capable of undertaking multiple different continuous control tasks. In this paper, we present a Knowledge Transfer based Multi-task Deep Reinforcement Learning framework (KTM-DRL) for continuous control, which enables a single DRL agent to achieve expert-level performance in multiple different tasks by learning from task-specific teachers. In KTM-DRL, the multi-task agent first leverages an offline knowledge transfer algorithm designed particularly for the actor-critic architecture to quickly learn a control policy from the experience of task-specific teachers, and then it employs an online learning algorithm to further improve itself by learning from new online transition samples under the guidance of those teachers. We perform a comprehensive empirical study with two commonly-used benchmarks in the MuJoCo continuous control task suite. The experimental results well justify the effectiveness of KTM-DRL and its knowledge transfer and online learning algorithms, as well as its superiority over the state-of-the-art by a large margin.

cs.LG↗

arXiv2020

Muon Flux Measurement at China Jinping Underground Laboratory

China Jinping Underground Laboratory (CJPL) is ideal for studying solar-, geo-, and supernova neutrinos. A precise measurement of the cosmic-ray background would play an essential role in proceeding with the R\&D research for these MeV-scale neutrino experiments. Using a 1-ton prototype detector for the Jinping Neutrino Experiment (JNE), we detected 264 high-energy muon events from a 645.2-day dataset at the first phase of CJPL (CJPL-I), reconstructed their directions, and measured the cosmic-ray muon flux to be $(3.53\pm0.22_{\text{stat.}}\pm0.07_{\text{sys.}})\times10^{-10}$ cm$^{-2}$s$^{-1}$. The observed angular distributions indicate the leakage of cosmic-ray muon background and agree with the simulation accounting for Jinping mountain's terrain. A survey of muon fluxes at different laboratory locations situated under mountains and below mine shaft indicated that the former is generally a factor of $(4\pm2)$ larger than the latter with the same vertical overburden. This study provides a convenient back-of-the-envelope estimation for muon flux of an underground experiment.

physics.ins-det↗

arXiv2020

GraphMix: Improved Training of GNNs for Semi-Supervised Learning

We present GraphMix, a regularization method for Graph Neural Network based semi-supervised object classification, whereby we propose to train a fully-connected network jointly with the graph neural network via parameter sharing and interpolation-based regularization. Further, we provide a theoretical analysis of how GraphMix improves the generalization bounds of the underlying graph neural network, without making any assumptions about the "aggregation" layer or the depth of the graph neural networks. We experimentally validate this analysis by applying GraphMix to various architectures such as Graph Convolutional Networks, Graph Attention Networks and Graph-U-Net. Despite its simplicity, we demonstrate that GraphMix can consistently improve or closely match state-of-the-art performance using even simpler architectures such as Graph Convolutional Networks, across three established graph benchmarks: Cora, Citeseer and Pubmed citation network datasets, as well as three newly proposed datasets: Cora-Full, Co-author-CS and Co-author-Physics.

cs.LG↗

arXiv2020

Graph neural induction of value iteration

Many reinforcement learning tasks can benefit from explicit planning based on an internal model of the environment. Previously, such planning components have been incorporated through a neural network that partially aligns with the computational graph of value iteration. Such network have so far been focused on restrictive environments (e.g. grid-worlds), and modelled the planning procedure only indirectly. We relax these constraints, proposing a graph neural network (GNN) that executes the value iteration (VI) algorithm, across arbitrary environment models, with direct supervision on the intermediate steps of VI. The results indicate that GNNs are able to model value iteration accurately, recovering favourable metrics and policies across a variety of out-of-distribution tests. This suggests that GNN executors with strong supervision are a viable component within deep reinforcement learning systems.

cs.LG↗

arXiv2020

Global oscillation data analysis on the $3ν$ mixing without unitarity

We present results of a combined analysis in neutrino oscillations without unitarity assumption in the $3ν$ mixing picture. Constraints on neutrino mixing matrix elements are based on recent data from the reactor, solar and long-baseline accelerator neutrino oscillation experiments. The current data are consistent with the standard $3ν$ scheme. The precision on different matrix elements can be as good as a few percent at $3σ$ CL, and is mainly limited by the experimental statistical uncertainty. The $ν_e$ related elements are the most precisely measured among all sectors with the uncertainties $<20\%$. The measured leptonic CP violation is very close to the one assuming the standard $3ν$ mixing. The deviations on normalization and the unitarity triangle closure are confined within $\mathcal{O}(10^{-3})$, $\mathcal{O}(10^{-2})$ and $\mathcal{O}(10^{-1})$, for $ν_e$, $ν_μ$ and $ν_τ$ sectors, respectively. We look forward to the next-generation neutrino oscillation experiments \textit{such as} DUNE, T2HK, and JUNO, especially the precise measurements on $ν_τ$ oscillations, to significantly improve the precision of unitarity test on the $3ν$ mixing matrix.

hep-ph↗

arXiv2020

Differentiable Feature Aggregation Search for Knowledge Distillation

Knowledge distillation has become increasingly important in model compression. It boosts the performance of a miniaturized student network with the supervision of the output distribution and feature maps from a sophisticated teacher network. Some recent works introduce multi-teacher distillation to provide more supervision to the student network. However, the effectiveness of multi-teacher distillation methods are accompanied by costly computation resources. To tackle with both the efficiency and the effectiveness of knowledge distillation, we introduce the feature aggregation to imitate the multi-teacher distillation in the single-teacher distillation framework by extracting informative supervision from multiple teacher feature maps. Specifically, we introduce DFA, a two-stage Differentiable Feature Aggregation search method that motivated by DARTS in neural architecture search, to efficiently find the aggregations. In the first stage, DFA formulates the searching problem as a bi-level optimization and leverages a novel bridge loss, which consists of a student-to-teacher path and a teacher-to-student path, to find appropriate feature aggregations. The two paths act as two players against each other, trying to optimize the unified architecture parameters to the opposite directions while guaranteeing both expressivity and learnability of the feature aggregation simultaneously. In the second stage, DFA performs knowledge distillation with the derived feature aggregation. Experimental results show that DFA outperforms existing methods on CIFAR-100 and CINIC-10 datasets under various teacher-student settings, verifying the effectiveness and robustness of the design.

cs.LG↗

arXiv2020

High-order minibands and interband Landau level reconstruction in graphene moire superlattice

The propagation of Dirac fermions in graphene through a long-period periodic potential would result in a band folding together with the emergence of a series of cloned Dirac points (DPs). In highly aligned graphene/hexagonal boron nitride (G/hBN) heterostructures, the lattice mismatch between the two atomic crystals generates a unique kind of periodic structure known as a moiré superlattice. Of particular interests is the emergent phenomena related to the reconstructed band-structure of graphene, such as the Hofstadter butterfly, topological currents, gate dependent pseudospin mixing, and ballistic miniband conduction. However, most studies so far have been limited to the lower-order minibands, e.g. the 1st and 2nd minibands counted from charge neutrality, and consequently the fundamental nature of the reconstructed higher-order miniband spectra still remains largely unknown. Here we report on probing the higher-order minibands of precisely aligned graphene moiré superlattices by transport spectroscopy. Using dual electrostatic gating, the edges of these high-order minibands, i.e. the 3rd and 4th minibands, can be reached. Interestingly, we have observed interband Landau level (LL) crossinginducing gap closures in a multiband magneto-transport regime, which originates from band overlap between the 2nd and 3rd minibands. As observed high-order minibands and LL reconstruction qualitatively match our simulated results. Our findings highlight the synergistic effect of minibands in transport, thus presenting a new opportunity for graphene electronic devices.

cond-mat.mes-hall↗

arXiv2020

Prospects and requirements of opaque detectors in accelerator neutrino experiments

Opaque detectors are a recently proposed novel detector concept where an opaque scintillator aligned with wavelength-shifting fibers is used to enable the discrimination of electron neutrinos and antineutrinos with a rather low energy threshold. In this work, we investigate the potential effects of the enhanced detection capabilities of the opaque detectors in accelerator neutrino experiments. Focusing on the energy threshold, energy resolution, detection efficiency and background suppression in the analysis of electron-like events, we determine whether using opaque detectors could lead to improvements in the CP violation and light sterile neutrino searches in the future accelerator neutrino experiments. We also identify the minimum requirements for the opaque detectors to reach the designated physics goals in the simulated experiments. We find that a 75.6% fraction of $δ_{CP}$ values could be reached for CP violation discovery by 3$σ$ confidence level or better when opaque detectors of 120 kton and 130 kton fiducial masses are used together with neutrino beams from J-PARC and MOMENT, respectively, whereas near detectors placed about 250 m from sources are sufficient to exclude the gallium anomaly at 2$σ$ confidence level.

physics.ins-det↗

arXiv2020

COVI White Paper

The SARS-CoV-2 (Covid-19) pandemic has caused significant strain on public health institutions around the world. Contact tracing is an essential tool to change the course of the Covid-19 pandemic. Manual contact tracing of Covid-19 cases has significant challenges that limit the ability of public health authorities to minimize community infections. Personalized peer-to-peer contact tracing through the use of mobile apps has the potential to shift the paradigm. Some countries have deployed centralized tracking systems, but more privacy-protecting decentralized systems offer much of the same benefit without concentrating data in the hands of a state authority or for-profit corporations. Machine learning methods can circumvent some of the limitations of standard digital tracing by incorporating many clues and their uncertainty into a more graded and precise estimation of infection risk. The estimated risk can provide early risk awareness, personalized recommendations and relevant information to the user. Finally, non-identifying risk data can inform epidemiological models trained jointly with the machine learning predictor. These models can provide statistical evidence for the importance of factors involved in disease transmission. They can also be used to monitor, evaluate and optimize health policy and (de)confinement scenarios according to medical and economic productivity indicators. However, such a strategy based on mobile apps and machine learning should proactively mitigate potential ethical and privacy risks, which could have substantial impacts on society (not only impacts on health but also impacts such as stigmatization and abuse of personal data). Here, we present an overview of the rationale, design, ethical considerations and privacy strategy of `COVI,' a Covid-19 public peer-to-peer contact tracing and risk awareness mobile application developed in Canada.

cs.CR↗

arXiv2020

GMNN: Graph Markov Neural Networks

This paper studies semi-supervised object classification in relational data, which is a fundamental problem in relational data modeling. The problem has been extensively studied in the literature of both statistical relational learning (e.g. relational Markov networks) and graph neural networks (e.g. graph convolutional networks). Statistical relational learning methods can effectively model the dependency of object labels through conditional random fields for collective classification, whereas graph neural networks learn effective object representations for classification through end-to-end training. In this paper, we propose the Graph Markov Neural Network (GMNN) that combines the advantages of both worlds. A GMNN models the joint distribution of object labels with a conditional random field, which can be effectively trained with the variational EM algorithm. In the E-step, one graph neural network learns effective object representations for approximating the posterior distributions of object labels. In the M-step, another graph neural network is used to model the local label dependency. Experiments on object classification, link classification, and unsupervised node representation learning show that GMNN achieves state-of-the-art results.

cs.LG↗

arXiv2020

Continuous Graph Neural Networks

This paper builds on the connection between graph neural networks and traditional dynamical systems. We propose continuous graph neural networks (CGNN), which generalise existing graph neural networks with discrete dynamics in that they can be viewed as a specific discretisation scheme. The key idea is how to characterise the continuous dynamics of node representations, i.e. the derivatives of node representations, w.r.t. time. Inspired by existing diffusion-based methods on graphs (e.g. PageRank and epidemic models on social networks), we define the derivatives as a combination of the current node representations, the representations of neighbors, and the initial values of the nodes. We propose and analyse two possible dynamics on graphs---including each dimension of node representations (a.k.a. the feature channel) change independently or interact with each other---both with theoretical justification. The proposed continuous graph neural networks are robust to over-smoothing and hence allow us to build deeper networks, which in turn are able to capture the long-range dependencies between nodes. Experimental results on the task of node classification demonstrate the effectiveness of our proposed approach over competitive baselines.

cs.LG↗

arXiv2020

Flavour Symmetry Embedded -- GLoBES (FaSE-GLoBES)

Neutrino models based on flavour symmetries provide the natural way to explain the origin of tiny neutrino masses. At the dawn of precision measurements of neutrino mixing parameters, neutrino mass models can be constrained and examined by on-going and up-coming neutrino experiments. We present a supplemental tool Flavour Symmetry Embedded (FaSE) for General Long Baseline Experiment Simulator (GLoBES), and it is available via the link https://github.com/tcwphy/FASE_GLoBES. It can translate the neutrino mass model parameters to standard neutrino oscillation parameters and offer prior functions in a user-friendly way. We demonstrate the robustness of FaSE-GLoBE with four examples on how the model parameters can be constrained and even whether the model is excluded by an experiment or not. We wish that this toolkit will facilitate the study of new neutrino mass models in an effecient and effective manner.

hep-ph↗

arXiv2020

An Image Enhancing Pattern-based Sparsity for Real-time Inference on Mobile Devices

Weight pruning has been widely acknowledged as a straightforward and effective method to eliminate redundancy in Deep Neural Networks (DNN), thereby achieving acceleration on various platforms. However, most of the pruning techniques are essentially trade-offs between model accuracy and regularity which lead to impaired inference accuracy and limited on-device acceleration performance. To solve the problem, we introduce a new sparsity dimension, namely pattern-based sparsity that comprises pattern and connectivity sparsity, and becoming both highly accurate and hardware friendly. With carefully designed patterns, the proposed pruning unprecedentedly and consistently achieves accuracy enhancement and better feature extraction ability on different DNN structures and datasets, and our pattern-aware pruning framework also achieves pattern library extraction, pattern selection, pattern and connectivity pruning and weight training simultaneously. Our approach on the new pattern-based sparsity naturally fits into compiler optimization for highly efficient DNN execution on mobile platforms. To the best of our knowledge, it is the first time that mobile devices achieve real-time inference for the large-scale DNN models thanks to the unique spatial property of pattern-based sparsity and the help of the code generation capability of compilers.

cs.CV↗