arXiv subjects

Zheng Zhang

Publications and source records attributed to Zheng Zhang.

At least 541 records · Page 30Linked to original sources

arXiv2021

Non-convex primal-dual algorithm for image reconstruction in spectral CT

The work seeks to develop an algorithm for image reconstruction by directly inverting the non-linear data model in spectral CT. Using the non-linear data model, we formulate the image-reconstruction problem as a non-convex optimization program, and develop a non-convex primal-dual (NCPD) algorithm to solve the program. We devise multiple convergence conditions and perform verification studies numerically to demonstrate that the NCPD algorithm can solve the non-convex optimization program and under appropriate data condition, can invert the non-linear data model. Using the NCPD algorithm, we then reconstruct monochromatic images from simulated and real data of numerical and physical phantoms acquired with a standard, full-scan dual-energy configuration. The result of the reconstruction studies shows that the NCPD algorithm can correct accurately for the non-linear beam-hardening effect. Furthermore, we apply the NCPD algorithm to simulated and real data of the numerical and physical phantoms collected with non-standard, short-scan dual-energy configurations, and obtain monochromatic images comparable to those of the standard, full-scan study, thus revealing the potential of the NCPD algorithm for enabling non-standard scanning configurations in spectral CT, where the existing indirect methods are limited.

physics.med-ph↗

arXiv2021

Dense Residual Network: Enhancing Global Dense Feature Flow for Character Recognition

Deep Convolutional Neural Networks (CNNs), such as Dense Convolutional Networks (DenseNet), have achieved great success for image representation by discovering deep hierarchical information. However, most existing networks simply stacks the convolutional layers and hence failing to fully discover local and global feature information among layers. In this paper, we mainly explore how to enhance the local and global dense feature flow by exploiting hierarchical features fully from all the convolution layers. Technically, we propose an efficient and effective CNN framework, i.e., Fast Dense Residual Network (FDRN), for text recognition. To construct FDRN, we propose a new fast residual dense block (f-RDB) to retain the ability of local feature fusion and local residual learning of original RDB, which can reduce the computing efforts at the same time. After fully learning local residual dense features, we utilize the sum operation and several f-RDBs to define a new block termed global dense block (GDB) by imitating the construction of dense blocks to learn global dense residual features adaptively in a holistic way. Finally, we use two convolution layers to construct a down-sampling block to reduce the global feature size and extract deeper features. Extensive simulations show that FDRN obtains the enhanced recognition results, compared with other related models.

cs.CV↗

arXiv2021

High-Dimensional Uncertainty Quantification via Active and Rank-Adaptive Tensor Regression

Uncertainty quantification based on stochastic spectral methods suffers from the curse of dimensionality. This issue was mitigated recently by low-rank tensor methods. However, there exist two fundamental challenges in low-rank tensor-based uncertainty quantification: how to automatically determine the tensor rank and how to pick the simulation samples. This paper proposes a novel tensor regression method to address these two challenges. Our method uses an $\ell_{q}/ \ell_{2}$-norm regularization to determine the tensor rank and an estimated Voronoi diagram to pick informative samples for simulation. The proposed framework is verified by a 19-dim phonics bandpass filter and a 57-dim CMOS ring oscillator, capturing the high-dimensional uncertainty well with only 90 and 290 samples respectively.

math.NA↗

arXiv2021

Fork or Fail: Cycle-Consistent Training with Many-to-One Mappings

Cycle-consistent training is widely used for jointly learning a forward and inverse mapping between two domains of interest without the cumbersome requirement of collecting matched pairs within each domain. In this regard, the implicit assumption is that there exists (at least approximately) a ground-truth bijection such that a given input from either domain can be accurately reconstructed from successive application of the respective mappings. But in many applications no such bijection can be expected to exist and large reconstruction errors can compromise the success of cycle-consistent training. As one important instance of this limitation, we consider practically-relevant situations where there exists a many-to-one or surjective mapping between domains. To address this regime, we develop a conditional variational autoencoder (CVAE) approach that can be viewed as converting surjective mappings to implicit bijections whereby reconstruction errors in both directions can be minimized, and as a natural byproduct, realistic output diversity can be obtained in the one-to-many direction. As theoretical motivation, we analyze a simplified scenario whereby minima of the proposed CVAE-based energy function align with the recovery of ground-truth surjective mappings. On the empirical side, we consider a synthetic image dataset with known ground-truth, as well as a real-world application involving natural language generation from knowledge graphs and vice versa, a prototypical surjective case. For the latter, our CVAE pipeline can capture such many-to-one mappings during cycle training while promoting textural diversity for graph-to-text tasks. Our code is available at github.com/QipengGuo/CycleGT *A condensed version of this paper has been accepted to AISTATS 2021. This version contains additional content and updates.

cs.LG↗

arXiv2021

Entropy-Based Uncertainty Calibration for Generalized Zero-Shot Learning

Compared to conventional zero-shot learning (ZSL) where recognising unseen classes is the primary or only aim, the goal of generalized zero-shot learning (GZSL) is to recognise both seen and unseen classes. Most GZSL methods typically learn to synthesise visual representations from semantic information on the unseen classes. However, these types of models are prone to overfitting the seen classes, resulting in distribution overlap between the generated features of the seen and unseen classes. The overlapping region is filled with uncertainty as the model struggles to determine whether a test case from within the overlap is seen or unseen. Further, these generative methods suffer in scenarios with sparse training samples. The models struggle to learn the distribution of high dimensional visual features and, therefore, fail to capture the most discriminative inter-class features. To address these issues, in this paper, we propose a novel framework that leverages dual variational autoencoders with a triplet loss to learn discriminative latent features and applies the entropy-based calibration to minimize the uncertainty in the overlapped area between the seen and unseen classes. Specifically, the dual generative model with the triplet loss synthesises inter-class discriminative latent features that can be mapped from either visual or semantic space. To calibrate the uncertainty for seen classes, we calculate the entropy over the softmax probability distribution from a general classifier. With this approach, recognising the seen samples within the seen classes is relatively straightforward, and there is less risk that a seen sample will be misclassified into an unseen class in the overlapped region. Extensive experiments on six benchmark datasets demonstrate that the proposed method outperforms state-of-the-art approaches.

cs.CV↗

arXiv2021

Effective Occlusion Handling for Fast Correlation Filter-based Trackers

Correlation filter-based trackers heavily suffer from the problem of multiple peaks in their response maps incurred by occlusions. Moreover, the whole tracking pipeline may break down due to the uncertainties brought by shifting among peaks, which will further lead to the degraded correlation filter model. To alleviate the drift problem caused by occlusions, we propose a novel scheme to choose the specific filter model according to different scenarios. Specifically, an effective measurement function is designed to evaluate the quality of filter response. A sophisticated strategy is employed to judge whether occlusions occur, and then decide how to update the filter models. In addition, we take advantage of both log-polar method and pyramid-like approach to estimate the best scale of the target. We evaluate our proposed approach on VOT2018 challenge and OTB100 dataset, whose experimental result shows that the proposed tracker achieves the promising performance compared against the state-of-the-art trackers.

cs.CV↗

arXiv2020

CycleGT: Unsupervised Graph-to-Text and Text-to-Graph Generation via Cycle Training

Two important tasks at the intersection of knowledge graphs and natural language processing are graph-to-text (G2T) and text-to-graph (T2G) conversion. Due to the difficulty and high cost of data collection, the supervised data available in the two fields are usually on the magnitude of tens of thousands, for example, 18K in the WebNLG~2017 dataset after preprocessing, which is far fewer than the millions of data for other tasks such as machine translation. Consequently, deep learning models for G2T and T2G suffer largely from scarce training data. We present CycleGT, an unsupervised training method that can bootstrap from fully non-parallel graph and text data, and iteratively back translate between the two forms. Experiments on WebNLG datasets show that our unsupervised model trained on the same number of data achieves performance on par with several fully supervised models. Further experiments on the non-parallel GenWiki dataset verify that our method performs the best among unsupervised baselines. This validates our framework as an effective approach to overcome the data scarcity problem in the fields of G2T and T2G. Our code is available at https://github.com/QipengGuo/CycleGT.

cs.CL↗

arXiv2020

Chiral phase transition inside a rotating cylinder within the Nambu--Jona-Lasinio model

We study the chiral phase transition inside a rotating cylinder within the framework of the Namb--Jona-Lasinio model. A spectral boundary condition is imposed to avoid faster than light. We investigate how the geometry of the cylinder and rotation influence the chiral phase transition at finite temperature and chemical potential. The inhomogeneous effects caused by the finite size and rotation are also taken into account. It is found that finite size will reduce the chiral transition temperature and raises the chiral transition chemical potential, while the rotation reduces both the chiral transition temperature and chemical potential. In addition, we discuss the implications of our results in heavy-ion collisions and equation of states of neutron star.

hep-ph↗

arXiv2020

Effective Magnetic Hamiltonian at Finite Temperatures for Rare Earth Chalcogenides

Alkali metal rare-earth chalcogenide $ARECh2$ (A=alkali or monovalent metal, RE=rare earth, Ch=O, S, Se, Te), is a large family of quantum spin liquid (QSL) candidates we discovered recently. Unlike $YbMgGaO4$, most members in the family except for the oxide ones, have relatively small crystalline electric-field (CEF) excitation levels, particularly the first ones. This makes the conventional Curie-Weiss analysis at finite temperatures inapplicable and CEF excitations may play an essential role in understanding the low-energy spin physics. Here we considered an effective magnetic Hamiltonian incorporating CEF excitations and spin-spin interactions, to accurately describe thermodynamics in such a system. By taking $NaYbSe2$ as an example, we were able to analyze magnetic susceptibility, magnetization under pulsed high fields and heat capacity in a systematic and comprehensive way. The analysis allows us to produce accurate anisotropic exchange coupling energies and unambiguously determine a crossover temperature ($\sim$25 K in the case of $NaYbSe2$), below which CEF effects fade away and pure spin-spin interactions stand out. We further validated the effective picture by successfully explaining the anomalous temperature dependence of electron spin resonance (ESR) spectral width. The effective scenario in principle can be generalized to other rare-earth spin systems with small CEF excitations.

cond-mat.str-el↗

arXiv2020

Overview of the Ninth Dialog System Technology Challenge: DSTC9

This paper introduces the Ninth Dialog System Technology Challenge (DSTC-9). This edition of the DSTC focuses on applying end-to-end dialog technologies for four distinct tasks in dialog systems, namely, 1. Task-oriented dialog Modeling with unstructured knowledge access, 2. Multi-domain task-oriented dialog, 3. Interactive evaluation of dialog, and 4. Situated interactive multi-modal dialog. This paper describes the task definition, provided datasets, baselines and evaluation set-up for each track. We also summarize the results of the submitted systems to highlight the overall trends of the state-of-the-art technologies for the tasks.

cs.CL↗

arXiv2020

Sparse Tucker Tensor Decomposition on a Hybrid FPGA-CPU Platform

Recommendation systems, social network analysis, medical imaging, and data mining often involve processing sparse high-dimensional data. Such high-dimensional data are naturally represented as tensors, and they cannot be efficiently processed by conventional matrix or vector computations. Sparse Tucker decomposition is an important algorithm for compressing and analyzing these sparse high-dimensional data sets. When energy efficiency and data privacy are major concerns, hardware accelerators on resource-constraint platforms become crucial for the deployment of tensor algorithms. In this work, we propose a hybrid computing framework containing CPU and FPGA to accelerate sparse Tucker factorization. This algorithm has three main modules: tensor-times-matrix (TTM), Kronecker products, and QR decomposition with column pivoting (QRP). In addition, we accelerate the former two modules on a Xilinx FPGA and the latter one on a CPU. Our hybrid platform achieves $23.6 \times \sim 1091\times$ speedup and over $93.519\% \sim 99.514 \%$ energy savings compared with CPU on the synthetic and real-world datasets.

cs.DC↗

arXiv2020

Relation of the Relations: A New Paradigm of the Relation Extraction Problem

In natural language, often multiple entities appear in the same text. However, most previous works in Relation Extraction (RE) limit the scope to identifying the relation between two entities at a time. Such an approach induces a quadratic computation time, and also overlooks the interdependency between multiple relations, namely the relation of relations (RoR). Due to the significance of RoR in existing datasets, we propose a new paradigm of RE that considers as a whole the predictions of all relations in the same context. Accordingly, we develop a data-driven approach that does not require hand-crafted rules but learns by itself the RoR, using Graph Neural Networks and a relation matrix transformer. Experiments show that our model outperforms the state-of-the-art approaches by +1.12\% on the ACE05 dataset and +2.55\% on SemEval 2018 Task 7.2, which is a substantial improvement on the two competitive benchmarks.

cs.CL↗

arXiv2020

CoLAKE: Contextualized Language and Knowledge Embedding

With the emerging branch of incorporating factual knowledge into pre-trained language models such as BERT, most existing models consider shallow, static, and separately pre-trained entity embeddings, which limits the performance gains of these models. Few works explore the potential of deep contextualized knowledge representation when injecting knowledge. In this paper, we propose the Contextualized Language and Knowledge Embedding (CoLAKE), which jointly learns contextualized representation for both language and knowledge with the extended MLM objective. Instead of injecting only entity embeddings, CoLAKE extracts the knowledge context of an entity from large-scale knowledge bases. To handle the heterogeneity of knowledge context and language context, we integrate them in a unified data structure, word-knowledge graph (WK graph). CoLAKE is pre-trained on large-scale WK graphs with the modified Transformer encoder. We conduct experiments on knowledge-driven tasks, knowledge probing tasks, and language understanding tasks. Experimental results show that CoLAKE outperforms previous counterparts on most of the tasks. Besides, CoLAKE achieves surprisingly high performance on our synthetic task called word-knowledge graph completion, which shows the superiority of simultaneously contextualizing language and knowledge representation.

cs.CL↗

arXiv2020

FeatGraph: A Flexible and Efficient Backend for Graph Neural Network Systems

Graph neural networks (GNNs) are gaining increasing popularity as a promising approach to machine learning on graphs. Unlike traditional graph workloads where each vertex/edge is associated with a scalar, GNNs attach a feature tensor to each vertex/edge. This additional feature dimension, along with consequently more complex vertex- and edge-wise computations, has enormous implications on locality and parallelism, which existing graph processing systems fail to exploit. This paper proposes FeatGraph to accelerate GNN workloads by co-optimizing graph traversal and feature dimension computation. FeatGraph provides a flexible programming interface to express diverse GNN models by composing coarse-grained sparse templates with fine-grained user-defined functions (UDFs) on each vertex/edge. FeatGraph incorporates optimizations for graph traversal into the sparse templates and allows users to specify optimizations for UDFs with a feature dimension schedule (FDS). FeatGraph speeds up end-to-end GNN training and inference by up to 32x on CPU and 7x on GPU.

cs.LG↗

arXiv2020

The Impact of Tandem Redundant/Sky-Based Calibration in MWA Phase II Data Analysis

Precise instrumental calibration is of crucial importance to 21-cm cosmology experiments. The Murchison Widefield Array's (MWA) Phase II compact configuration offers us opportunities for both redundant calibration and sky-based calibration algorithms; using the two in tandem is a potential approach to mitigate calibration errors caused by inaccurate sky models. The MWA Epoch of Reionization (EoR) experiment targets three patches of the sky (dubbed EoR0, EoR1, and EoR2) with deep observations. Previous work in \cite{Li_2018} and \cite{Wenyang_2019} studied the effect of tandem calibration on the EoR0 field and found that it yielded no significant improvement in the power spectrum over sky-based calibration alone. In this work, we apply similar techniques to the EoR1 field and find a distinct result: the improvements in the power spectrum from tandem calibration are significant. To understand this result, we analyze both the calibration solutions themselves and the effects on the power spectrum over three nights of EoR1 observations. We conclude that the presence of the bright radio galaxy Fornax A in EoR1 degrades the performance of sky-based calibration, which in turn enables redundant calibration to have a larger impact. These results suggest that redundant calibration can indeed mitigate some level of model-incompleteness error.

astro-ph.IM↗

arXiv2020

Disentangled Non-Local Neural Networks

The non-local block is a popular module for strengthening the context modeling ability of a regular convolutional neural network. This paper first studies the non-local block in depth, where we find that its attention computation can be split into two terms, a whitened pairwise term accounting for the relationship between two pixels and a unary term representing the saliency of every pixel. We also observe that the two terms trained alone tend to model different visual clues, e.g. the whitened pairwise term learns within-region relationships while the unary term learns salient boundaries. However, the two terms are tightly coupled in the non-local block, which hinders the learning of each. Based on these findings, we present the disentangled non-local block, where the two terms are decoupled to facilitate learning for both terms. We demonstrate the effectiveness of the decoupled design on various tasks, such as semantic segmentation on Cityscapes, ADE20K and PASCAL Context, object detection on COCO, and action recognition on Kinetics.

cs.CV↗

arXiv2020

Spatially Adaptive Inference with Stochastic Feature Sampling and Interpolation

In the feature maps of CNNs, there commonly exists considerable spatial redundancy that leads to much repetitive processing. Towards reducing this superfluous computation, we propose to compute features only at sparsely sampled locations, which are probabilistically chosen according to activation responses, and then densely reconstruct the feature map with an efficient interpolation procedure. With this sampling-interpolation scheme, our network avoids expending computation on spatial locations that can be effectively interpolated, while being robust to activation prediction errors through broadly distributed sampling. A technical challenge of this sampling-based approach is that the binary decision variables for representing discrete sampling locations are non-differentiable, making them incompatible with backpropagation. To circumvent this issue, we make use of a reparameterization trick based on the Gumbel-Softmax distribution, with which backpropagation can iterate these variables towards binary values. The presented network is experimentally shown to save substantial computation while maintaining accuracy over a variety of computer vision tasks.

cs.CV↗

arXiv2020

Quantum-Inspired Hamiltonian Monte Carlo for Bayesian Sampling

Hamiltonian Monte Carlo (HMC) is an efficient Bayesian sampling method that can make distant proposals in the parameter space by simulating a Hamiltonian dynamical system. Despite its popularity in machine learning and data science, HMC is inefficient to sample from spiky and multimodal distributions. Motivated by the energy-time uncertainty relation from quantum mechanics, we propose a Quantum-Inspired Hamiltonian Monte Carlo algorithm (QHMC). This algorithm allows a particle to have a random mass matrix with a probability distribution rather than a fixed mass. We prove the convergence property of QHMC and further show why such a random mass can improve the performance when we sample a broad class of distributions. In order to handle the big training data sets in large-scale machine learning, we develop a stochastic gradient version of QHMC using Nos{é}-Hoover thermostat called QSGNHT, and we also provide theoretical justifications about its steady-state distributions. Finally in the experiments, we demonstrate the effectiveness of QHMC and QSGNHT on synthetic examples, bridge regression, image denoising and neural network pruning. The proposed QHMC and QSGNHT can indeed achieve much more stable and accurate sampling results on the test cases.

stat.ML↗