arXiv subjects

Haoran Wang

Publications and source records attributed to Haoran Wang.

At least 217 records · Page 12Linked to original sources

arXiv2022

Tolerance For the Pixelation Effect in Shear Measurement

Images taken by space telescopes typically have a superb spatial resolution, but a relatively poor sampling rate due to the finite CCD pixel size. Beyond the Nyquist limit, it becomes uncertain how much the pixelation effect may affect the accuracy of galaxy shape measurement. It is timely to study this issue given that a number of space-based large-scale weak lensing surveys are planned. Using the Fourier_Quad method, we quantify the shear recovery error as a function of the sampling factor Q, i.e., the ratio between the FWHM of the point-spread-function (PSF) and the pixel size of the CCD, for different PSFs and galaxies of different sizes and noise levels. We show that sub-percent-level accuracy in shear recovery is achievable with single-exposure images for $Q\lesssim 2$. The conclusion holds for galaxies much smaller than the PSF, and those with a significant level of noise.

astro-ph.CO↗

arXiv2022

CONet: Channel Optimization for Convolutional Neural Networks

Neural Architecture Search (NAS) has shifted network design from using human intuition to leveraging search algorithms guided by evaluation metrics. We study channel size optimization in convolutional neural networks (CNN) and identify the role it plays in model accuracy and complexity. Current channel size selection methods are generally limited by discrete sample spaces while suffering from manual iteration and simple heuristics. To solve this, we introduce an efficient dynamic scaling algorithm -- CONet -- that automatically optimizes channel sizes across network layers for a given CNN. Two metrics -- "\textit{Rank}" and "\textit{Rank Average Slope}" -- are introduced to identify the information accumulated in training. The algorithm dynamically scales channel sizes up or down over a fixed searching phase. We conduct experiments on CIFAR10/100 and ImageNet datasets and show that CONet can find efficient and accurate architectures searched in ResNet, DARTS, and DARTS+ spaces that outperform their baseline models. This document supersedes previously published paper in ICCV2021-NeurArch workshop. An additional section is included on manual scaling of channel size in CNNs to numerically validate of the metrics used in searching optimum channel configurations in CNNs.

cs.CV↗

arXiv2022

Maximal estimates for fractional Schrödinger equations in scaling critical magnetic fields

In this paper, we combine the argument of [12] and [27] to prove the maximal estimates for fractional Schrödinger equations $(i\partial_t+\mathcal{L}_{\mathbf{A}}^{\fracα2})u=0$ in the purely magnetic fields which includes the Aharonov-Bohm fields. The proof is based on the cluster spectral measure estimates. In particular $α=1$, the maximal estimate for wave equation is sharp up to the endpoint.

math.AP↗

arXiv2021

Can multi-label classification networks know what they don't know?

Estimating out-of-distribution (OOD) uncertainty is a central challenge for safely deploying machine learning models in the open-world environment. Improved methods for OOD detection in multi-class classification have emerged, while OOD detection methods for multi-label classification remain underexplored and use rudimentary techniques. We propose JointEnergy, a simple and effective method, which estimates the OOD indicator scores by aggregating energy scores from multiple labels. We show that JointEnergy can be mathematically interpreted from a joint likelihood perspective. Our results show consistent improvement over previous methods that are based on the maximum-valued scores, which fail to capture joint information from multiple labels. We demonstrate the effectiveness of our method on three common multi-label classification benchmarks, including MS-COCO, PASCAL-VOC, and NUS-WIDE. We show that JointEnergy can reduce the FPR95 by up to 10.05% compared to the previous best baseline, establishing state-of-the-art performance.

cs.LG↗

arXiv2021

Emily: Developing An Emotion-affective Open-Domain Chatbot with Knowledge Graph-based Persona

In this paper, we describe approaches for developing Emily, an emotion-affective open-domain chatbot. Emily can perceive a user's negative emotion state and offer supports by positively converting the user's emotion states. This is done by finetuning a pretrained dialogue model upon data capturing dialogue contexts and desirable emotion states transition across turns. Emily can differentiate a general open-domain dialogue utterance with questions relating to personal information. By leveraging a question-answering approach based on knowledge graphs to handle personal information, Emily maintains personality consistency. We evaluate Emily against a few state-of-the-art open-domain chatbots and show the effects of the proposed approaches in emotion affecting and addressing personality inconsistency.

cs.CL↗

arXiv2021

Exploring Fluent Query Reformulations with Text-to-Text Transformers and Reinforcement Learning

Query reformulation aims to alter noisy or ambiguous text sequences into coherent ones closer to natural language questions. This is to prevent errors from propagating in a client-facing pipeline and promote better communication with users. Besides, it is crucial to maintain performance in downstream environments like question answering when rephrased queries are given as input. We show that under the previous framework (AQA), attempts to alter RL algorithms do not bring significant benefits to either reward acquisition or sequence fluency. Instead, we leverage a query-reformulating text-to-text transformer (QRT5) and apply policy-based RL algorithms to further nudge this reformulator and obtain better answers downstream by generating reward-acquiring query trajectories. QRT5 shows better sample efficiency in RL to achieve the same level of QA performance as the previous approach. It can generate reformulations with more readability based on query well-formedness evaluations and can generalize to out-of-sample data. Our framework is demonstrated to be flexible, allowing reward signals to be sourced from different downstream environments such as intent classification.

cs.CL↗

arXiv2021

Step-Wise Hierarchical Alignment Network for Image-Text Matching

Image-text matching plays a central role in bridging the semantic gap between vision and language. The key point to achieve precise visual-semantic alignment lies in capturing the fine-grained cross-modal correspondence between image and text. Most previous methods rely on single-step reasoning to discover the visual-semantic interactions, which lacks the ability of exploiting the multi-level information to locate the hierarchical fine-grained relevance. Different from them, in this work, we propose a step-wise hierarchical alignment network (SHAN) that decomposes image-text matching into multi-step cross-modal reasoning process. Specifically, we first achieve local-to-local alignment at fragment level, following by performing global-to-local and global-to-global alignment at context level sequentially. This progressive alignment strategy supplies our model with more complementary and sufficient semantic clues to understand the hierarchical correlations between image and text. The experimental results on two benchmark datasets demonstrate the superiority of our proposed method.

cs.CV↗

arXiv2021

Robo-Advising: Enhancing Investment with Inverse Optimization and Deep Reinforcement Learning

Machine Learning (ML) has been embraced as a powerful tool by the financial industry, with notable applications spreading in various domains including investment management. In this work, we propose a full-cycle data-driven investment robo-advising framework, consisting of two ML agents. The first agent, an inverse portfolio optimization agent, infers an investor's risk preference and expected return directly from historical allocation data using online inverse optimization. The second agent, a deep reinforcement learning (RL) agent, aggregates the inferred sequence of expected returns to formulate a new multi-period mean-variance portfolio optimization problem that can be solved using deep RL approaches. The proposed investment pipeline is applied on real market data from April 1, 2016 to February 1, 2021 and has shown to consistently outperform the S&P 500 benchmark portfolio that represents the aggregate market optimal allocation. The outperformance may be attributed to the the multi-period planning (versus single-period planning) and the data-driven RL approach (versus classical estimation approach).

q-fin.PM↗

arXiv2021

Saliency-Guided Attention Network for Image-Sentence Matching

This paper studies the task of matching image and sentence, where learning appropriate representations across the multi-modal data appears to be the main challenge. Unlike previous approaches that predominantly deploy symmetrical architecture to represent both modalities, we propose Saliency-guided Attention Network (SAN) that asymmetrically employs visual and textual attention modules to learn the fine-grained correlation intertwined between vision and language. The proposed SAN mainly includes three components: saliency detector, Saliency-weighted Visual Attention (SVA) module, and Saliency-guided Textual Attention (STA) module. Concretely, the saliency detector provides the visual saliency information as the guidance for the two attention modules. SVA is designed to leverage the advantage of the saliency information to improve discrimination of visual representations. By fusing the visual information from SVA and textual information as a multi-modal guidance, STA learns discriminative textual representations that are highly sensitive to visual clues. Extensive experiments demonstrate SAN can substantially improve the state-of-the-art results on the benchmark Flickr30K and MSCOCO datasets by a large margin.

cs.CV↗

arXiv2021

Strictly Decentralized Adaptive Estimation of External Fields using Reproducing Kernels

This paper describes an adaptive method in continuous time for the estimation of external fields by a team of $N$ agents. The agents $i$ each explore subdomains $Ω^i$ of a bounded subset of interest $Ω\subset X := \mathbb{R}^d$. Ideal adaptive estimates $\hat{g}^i_t$ are derived for each agent from a distributed parameter system (DPS) that takes values in the scalar-valued reproducing kernel Hilbert space $H_X$ of functions over $X$. Approximations of the evolution of the ideal local estimate $\hat{g}^i_t$ of agent $i$ is constructed solely using observations made by agent $i$ on a fine time scale. Since the local estimates on the fine time scale are constructed independently for each agent, we say that the method is strictly decentralized. On a coarse time scale, the individual local estimates $\hat{g}^i_t$ are fused via the expression $\hat{g}_t:=\sum_{i=1}^NΨ^i \hat{g}^i_t$ that uses a partition of unity $\{Ψ^i\}_{1\leq i\leq N}$ subordinate to the cover $\{Ω^i\}_{i=1,\ldots,N}$ of $Ω$. Realizable algorithms are obtained by constructing finite dimensional approximations of the DPS in terms of scattered bases defined by each agent from samples along their trajectories. Rates of convergence of the error in the finite dimensional approximations are derived in terms of the fill distance of the samples that define the scattered centers in each subdomain. The qualitative performance of the convergence rates for the decentralized estimation method is illustrated via numerical simulations.

eess.SY↗

arXiv2021

Context-Aware Graph Convolution Network for Target Re-identification

Most existing re-identification methods focus on learning robust and discriminative features with deep convolution networks. However, many of them consider content similarity separately and fail to utilize the context information of the query and gallery sets, e.g. probe-gallery and gallery-gallery relations, thus hard samples may not be well solved due to the limited or even misleading information. In this paper, we present a novel Context-Aware Graph Convolution Network (CAGCN), where the probe-gallery relations are encoded into the graph nodes and the graph edge connections are well controlled by the gallery-gallery relations. In this way, hard samples can be addressed with the context information flows among other easy samples during the graph reasoning. Specifically, we adopt an effective hard gallery sampler to obtain high recall for positive samples while keeping a reasonable graph size, which can also weaken the imbalanced problem in training process with low computation complexity.Experiments show that the proposed method achieves state-of-the-art performance on both person and vehicle re-identification datasets in a plug and play fashion with limited overhead.

cs.CV↗

arXiv2021

Towards a Bias-Free Selection Function in Shear Measurement

Sample selection is a necessary preparation for weak lensing measurement. It is well-known that selection itself may introduce bias in the measured shear signal. Using image simulation and the Fourier_Quad shear measurement pipeline, we quantify the selection bias in various commonly used selection function (signal-to-noise-ratio, magnitude, etc.). We proposed a new selection function defined in the power spectrum of the galaxy image. This new selection function has low selection bias, and it is particularly convenient for shear measurement pipelines based on Fourier transformation.

astro-ph.CO↗

arXiv2021

Learning Risk Preferences from Investment Portfolios Using Inverse Optimization

The fundamental principle in Modern Portfolio Theory (MPT) is based on the quantification of the portfolio's risk related to performance. Although MPT has made huge impacts on the investment world and prompted the success and prevalence of passive investing, it still has shortcomings in real-world applications. One of the main challenges is that the level of risk an investor can endure, known as \emph{risk-preference}, is a subjective choice that is tightly related to psychology and behavioral science in decision making. This paper presents a novel approach of measuring risk preference from existing portfolios using inverse optimization on the mean-variance portfolio allocation framework. Our approach allows the learner to continuously estimate real-time risk preferences using concurrent observed portfolios and market price data. We demonstrate our methods on real market data that consists of 20 years of asset pricing and 10 years of mutual fund portfolio holdings. Moreover, the quantified risk preference parameters are validated with two well-known risk measurements currently applied in the field. The proposed methods could lead to practical and fruitful innovations in automated/personalized portfolio management, such as Robo-advising, to augment financial advisors' decision intelligence in a long-term investment horizon.

q-fin.PM↗

arXiv2021

Consensus-Aware Visual-Semantic Embedding for Image-Text Matching

Image-text matching plays a central role in bridging vision and language. Most existing approaches only rely on the image-text instance pair to learn their representations, thereby exploiting their matching relationships and making the corresponding alignments. Such approaches only exploit the superficial associations contained in the instance pairwise data, with no consideration of any external commonsense knowledge, which may hinder their capabilities to reason the higher-level relationships between image and text. In this paper, we propose a Consensus-aware Visual-Semantic Embedding (CVSE) model to incorporate the consensus information, namely the commonsense knowledge shared between both modalities, into image-text matching. Specifically, the consensus information is exploited by computing the statistical co-occurrence correlations between the semantic concepts from the image captioning corpus and deploying the constructed concept correlation graph to yield the consensus-aware concept (CAC) representations. Afterwards, CVSE learns the associations and alignments between image and text based on the exploited consensus as well as the instance-level representations for both modalities. Extensive experiments conducted on two public datasets verify that the exploited consensus makes significant contributions to constructing more meaningful visual-semantic embeddings, with the superior performances over the state-of-the-art approaches on the bidirectional image and text retrieval task. Our code of this paper is available at: https://github.com/BruceW91/CVSE.

cs.CV↗

arXiv2021

Majorana corner states in square and Kagome quantum spin liquids

Quantum spin liquids hosting Majorana excitations have recently experienced renewed interest for potential applications to topological quantum computation. Performing logical operations with reduced poisoning requires to localize such quasiparticles at specific point of the system, with energies that are well defined and inside the bulk energy gap. These are two defining features of second order topological insulators (SOTIs). Here, we show two spin models that support quantum spin liquid phases characterised by Majorana excitations and that behave as SOTIs, one of which is analytically solvable thanks to a theorem by Lieb. We show that, depending on the values of spin couplings, it is possible to localize either fermions or Majorana particles at their corners.

cond-mat.str-el↗

arXiv2020

Frame Aggregation and Multi-Modal Fusion Framework for Video-Based Person Recognition

Video-based person recognition is challenging due to persons being blocked and blurred, and the variation of shooting angle. Previous research always focused on person recognition on still images, ignoring similarity and continuity between video frames. To tackle the challenges above, we propose a novel Frame Aggregation and Multi-Modal Fusion (FAMF) framework for video-based person recognition, which aggregates face features and incorporates them with multi-modal information to identify persons in videos. For frame aggregation, we propose a novel trainable layer based on NetVLAD (named AttentionVLAD), which takes arbitrary number of features as input and computes a fixed-length aggregation feature based on feature quality. We show that introducing an attention mechanism to NetVLAD can effectively decrease the impact of low-quality frames. For the multi-model information of videos, we propose a Multi-Layer Multi-Modal Attention (MLMA) module to learn the correlation of multi-modality by adaptively updating Gram matrix. Experimental results on iQIYI-VID-2019 dataset show that our framework outperforms other state-of-the-art methods.

cs.CV↗

arXiv2020

Avoiding the Geometric Boundary Effect in Shear Measurement

In image processing, source detections are inevitably affected by the presence of the geometric boundaries in the images, including the physical boundaries of the CCD, and the boundaries of masked regions due to column defects, bright diffraction spikes, etc.. These boundary conditions make the source detection process not statistically isotropic. It can lead to additive shear bias near the boundaries. We build a phenomenological model to understand the bias, and propose a simple method to effectively eliminate the influence of geometric boundaries on shear measurement. We demonstrate the accuracy and efficiency of this method using both simulations and the z-band imaging data from the third data release of the DECam Legacy Survey.

astro-ph.IM↗

arXiv2020

Information Diffusion Prediction with Latent Factor Disentanglement

Information diffusion prediction is a fundamental task which forecasts how an information item will spread among users. In recent years, deep learning based methods, especially those based on recurrent neural networks (RNNs), have achieved promising results on this task by treating infected users as sequential data. However, existing methods represent all previously infected users by a single vector and could fail to encode all necessary information for future predictions due to the mode collapse problem. To address this problem, we propose to employ the idea of disentangled representation learning, which aims to extract multiple latent factors representing different aspects of the data, for modeling the information diffusion process. Specifically, we employ a sequential attention module and a disentangled attention module to better aggregate the history information and disentangle the latent factors. Experimental results on three real-world datasets show that the proposed model SIDDA significantly outperforms state-of-the-art baseline methods by up to 14% in terms of hits@N metric, which demonstrates the effectiveness of our method.

cs.SI↗