arXiv subjects

Jiawen Li

Publications and source records attributed to Jiawen Li.

68 records · Page 4Linked to original sources

arXiv2022

HIRL: A General Framework for Hierarchical Image Representation Learning

Learning self-supervised image representations has been broadly studied to boost various visual understanding tasks. Existing methods typically learn a single level of image semantics like pairwise semantic similarity or image clustering patterns. However, these methods can hardly capture multiple levels of semantic information that naturally exists in an image dataset, e.g., the semantic hierarchy of "Persian cat to cat to mammal" encoded in an image database for species. It is thus unknown whether an arbitrary image self-supervised learning (SSL) approach can benefit from learning such hierarchical semantics. To answer this question, we propose a general framework for Hierarchical Image Representation Learning (HIRL). This framework aims to learn multiple semantic representations for each image, and these representations are structured to encode image semantics from fine-grained to coarse-grained. Based on a probabilistic factorization, HIRL learns the most fine-grained semantics by an off-the-shelf image SSL approach and learns multiple coarse-grained semantics by a novel semantic path discrimination scheme. We adopt six representative image SSL methods as baselines and study how they perform under HIRL. By rigorous fair comparison, performance gain is observed on all the six methods for diverse downstream tasks, which, for the first time, verifies the general effectiveness of learning hierarchical image semantics. All source code and model weights are available at https://github.com/hirl-team/HIRL

cs.CV↗

arXiv2022

HCSC: Hierarchical Contrastive Selective Coding

Hierarchical semantic structures naturally exist in an image dataset, in which several semantically relevant image clusters can be further integrated into a larger cluster with coarser-grained semantics. Capturing such structures with image representations can greatly benefit the semantic understanding on various downstream tasks. Existing contrastive representation learning methods lack such an important model capability. In addition, the negative pairs used in these methods are not guaranteed to be semantically distinct, which could further hamper the structural correctness of learned image representations. To tackle these limitations, we propose a novel contrastive learning framework called Hierarchical Contrastive Selective Coding (HCSC). In this framework, a set of hierarchical prototypes are constructed and also dynamically updated to represent the hierarchical semantic structures underlying the data in the latent space. To make image representations better fit such semantic structures, we employ and further improve conventional instance-wise and prototypical contrastive learning via an elaborate pair selection scheme. This scheme seeks to select more diverse positive pairs with similar semantics and more precise negative pairs with truly distinct semantics. On extensive downstream tasks, we verify the superior performance of HCSC over state-of-the-art contrastive methods, and the effectiveness of major model components is proved by plentiful analytical studies. We build a comprehensive model zoo in Sec. D. Our source code and model weights are available at https://github.com/gyfastas/HCSC

cs.CV↗

arXiv2021

True or False: Does the Deep Learning Model Learn to Detect Rumors?

It is difficult for humans to distinguish the true and false of rumors, but current deep learning models can surpass humans and achieve excellent accuracy on many rumor datasets. In this paper, we investigate whether deep learning models that seem to perform well actually learn to detect rumors. We evaluate models on their generalization ability to out-of-domain examples by fine-tuning BERT-based models on five real-world datasets and evaluating against all test sets. The experimental results indicate that the generalization ability of the models on other unseen datasets are unsatisfactory, even common-sense rumors cannot be detected. Moreover, we found through experiments that models take shortcuts and learn absurd knowledge when the rumor datasets have serious data pitfalls. This means that simple modifications to the rumor text based on specific rules will lead to inconsistent model predictions. To more realistically evaluate rumor detection models, we proposed a new evaluation method called paired test (PairT), which requires models to correctly predict a pair of test samples at the same time. Furthermore, we make recommendations on how to better create rumor dataset and evaluate rumor detection model at the end of this paper.

cs.CL↗

arXiv2021

DropAttack: A Masked Weight Adversarial Training Method to Improve Generalization of Neural Networks

Adversarial training has been proven to be a powerful regularization method to improve the generalization of models. However, current adversarial training methods only attack the original input sample or the embedding vectors, and their attacks lack coverage and diversity. To further enhance the breadth and depth of attack, we propose a novel masked weight adversarial training method called DropAttack, which enhances generalization of model by adding intentionally worst-case adversarial perturbations to both the input and hidden layers in different dimensions and minimize the adversarial risks generated by each layer. DropAttack is a general technique and can be adopt to a wide variety of neural networks with different architectures. To validate the effectiveness of the proposed method, we used five public datasets in the fields of natural language processing (NLP) and computer vision (CV) for experimental evaluating. We compare the proposed method with other adversarial training methods and regularization methods, and our method achieves state-of-the-art on all datasets. In addition, Dropattack can achieve the same performance when it use only a half training data compared to other standard training method. Theoretical analysis reveals that DropAttack can perform gradient regularization at random on some of the input and wight parameters of the model. Further visualization experiments show that DropAttack can push the minimum risk of the model to a lower and flatter loss landscapes. Our source code is publicly available on https://github.com/nishiwen1214/DropAttack.

cs.LG↗

arXiv2021

Meet The Truth: Leverage Objective Facts and Subjective Views for Interpretable Rumor Detection

Existing rumor detection strategies typically provide detection labels while ignoring their explanation. Nonetheless, providing pieces of evidence to explain why a suspicious tweet is rumor is essential. As such, a novel model, LOSIRD, was proposed in this paper. First, LOSIRD mines appropriate evidence sentences and classifies them by automatically checking the veracity of the relationship of the given claim and its evidence from about 5 million Wikipedia documents. LOSIRD then automatically constructs two heterogeneous graph objects to simulate the propagation layout of the tweets and code the relationship of evidence. Finally, a graphSAGE processing component is used in LOSIRD to provide the label and evidence. To the best of our knowledge, we are the first one who combines objective facts and subjective views to verify rumor. The experimental results on two real-world Twitter datasets showed that our model exhibited the best performance in the early rumor detection task and its rumor detection performance outperformed other baseline and state-of-the-art models. Moreover, we confirmed that both objective information and subjective information are fundamental clues for rumor detection.

cs.SI↗

arXiv2020

Rumor Detection on Twitter Using Multiloss Hierarchical BiLSTM with an Attenuation Factor

Social media platforms such as Twitter have become a breeding ground for unverified information or rumors. These rumors can threaten people's health, endanger the economy, and affect the stability of a country. Many researchers have developed models to classify rumors using traditional machine learning or vanilla deep learning models. However, previous studies on rumor detection have achieved low precision and are time consuming. Inspired by the hierarchical model and multitask learning, a multiloss hierarchical BiLSTM model with an attenuation factor is proposed in this paper. The model is divided into two BiLSTM modules: post level and event level. By means of this hierarchical structure, the model can extract deep in-formation from limited quantities of text. Each module has a loss function that helps to learn bilateral features and reduce the training time. An attenuation fac-tor is added at the post level to increase the accuracy. The results on two rumor datasets demonstrate that our model achieves better performance than that of state-of-the-art machine learning and vanilla deep learning models.

cs.CL↗

arXiv2019

Convergence Rates of Subgradient Methods for Quasi-convex Optimization Problems

Quasi-convex optimization acts a pivotal part in many fields including economics and finance; the subgradient method is an effective iterative algorithm for solving large-scale quasi-convex optimization problems. In this paper, we investigate the iteration complexity and convergence rates of various subgradient methods for solving quasi-convex optimization in a unified framework. In particular, we consider a sequence satisfying a general (inexact) basic inequality, and investigate the global convergence theorem and the iteration complexity when using the constant, diminishing or dynamic stepsize rules. More importantly, we establish the linear (or sublinear) convergence rates of the sequence under an additional assumption of weak sharp minima of Hölderian order and upper bounded noise. These convergence theorems are applied to establish the iteration complexity and convergence rates of several subgradient methods, including the standard/inexact/conditional subgradient methods, for solving quasi-convex optimization problems under the assumptions of the Hölder condition and/or the weak sharp minima of Hölderian order.

math.OC↗

arXiv2019

Growth of massive black holes at high-z via accretion predominantly driven by magnetic outflows

Luminous quasars powered by accreting supermassive black holes (SMBHs) have been found in the early Universe at $z \gtrsim 7.5$, which set a strong constraint on both the seed black hole mass and the rapid growth of the SMBHs. In this work, we explore how the SMBHs are grown through Eddington limited accretion driven predominantly by magnetic outflows. Most angular momentum and the released gravitational energy in the disk can be removed by magnetic outflows, and therefore the mass accretion rate of the black hole (BH) can be high even if the disk is radiating at sub-Eddington luminosity. It is found that the SMBH with several billion solar masses discovered at $z\gtrsim 7$ may probably be grown through chaotic accretion predominantly driven by magnetic outflows from a stellar mass BH, when the disks are radiating at moderate luminosity ($\sim 0.5$ Eddington luminosity) with mild outflows. We find that most SMBHs are spinning at moderate values of spin parameter $a_*$, which implies only a small fraction of quasars may have radio jets.

astro-ph.HE↗

arXiv2019

Measurements of differential and angle-integrated cross sections for the $^{10}$B($n, α$)$^{7}$Li reaction in the neutron energy range from 1.0 eV to 2.5 MeV

Differential and angle-integrated cross sections for the $^{10}$B($n, α$)$^{7}$Li, $^{10}$B($n, α$$_{0}$)$^{7}$Li and $^{10}$B($n, α$$_{1}$)$^{7}$Li$^{*}$ reactions have been measured at CSNS Back-n white neutron source. Two enriched (90%) $^{10}$B samples 5.0 cm in diameter and ~85.0 $μ$g/cm$^{2}$ in thickness each with an aluminum backing were prepared, and back-to-back mounted at the sample holder. The charged particles were detected using the silicon-detector array of the Light-charged Particle Detector Array (LPDA) system. The neutron energy E$_{n}$ was determined by TOF (time-of-flight) method, and the valid $α$ events were extracted from the E$_{n}$-Amplitude two-dimensional spectrum. With 15 silicon detectors, the differential cross sections of $α$-particles were measured from 19.2° to 160.8°. Fitted with the Legendre polynomial series, the ($n, α$) cross sections were obtained through integration. The absolute cross sections were normalized using the standard cross sections of the $^{10}$B($n, α$)$^{7}$Li reaction in the 0.3 - 0.5 MeV neutron energy region. The measurement neutron energy range for the $^{10}$B($n, α$)$^{7}$Li reaction is 1.0 eV $\le$ En < 2.5 MeV (67 energy points), and for the $^{10}$B($n, α$$_{0}$)$^{7}$Li and $^{10}$B($n, α$$_{1}$)$^{7}$Li$^{*}$ reactions is 1.0 eV $\le$ En < 1.0 MeV (59 energy points). The present results have been analyzed by the resonance reaction mechanism and the level structure of the $^{11}$B compound system, and compared with existing measurements and evaluations.

nucl-ex↗

arXiv2019

The large-scale magnetic field of a thin accretion disk with outflows

The large-scale magnetic field threading an accretion disk plays an important role in launching jets/outflows. The field may probably be advected inwards by the plasma in the accretion disk from the ambient environment (interstellar medium or a companion star). It has been suggested that the external field can be efficiently dragged inwards in a thin disk with magnetic outflows. We construct a self-consistent global disk-outflow model, in which the large-scale field is formed by the advection of the external field in the disk. The outflows are accelerated by this field co-rotating with the disk, which carry away most angular momentum of the disk and make its structure significantly different from the conventional viscous disk structure. We find that the magnetic field strength in the inner region of the disk can be several orders of magnitude higher than the external field strength for a geometrically thin disk with $H/R \sim 0.1$, if the ratio of the gas to magnetic pressure $β_{\rm out} \sim 10^2 $ at the outer edge of the disk. The outflow velocity shows layer-like structure, i.e., it decreases with radius where it is launched. The outflow can be accelerated up to $ \sim 0.2-0.3$c from the inner region of the disk, and the mass loss rate in the outflows is $ \sim 10 - 70\%$ of the mass accretion rate at the outer radius of the disk, which may account for the fast outflows observed in some active galactic nuclei (AGNs).

astro-ph.HE↗

arXiv2018

Ultra-sensitive Experimental Detection of Chiral Meso-structures by Orbital Angular Momentum of Light

Circular dichroism (CD) induced by spin angular momentum of light is vital to investigate the chirality of microscopic objects such as molecules, proteins and metamaterials. However, orbital angular momentum (OAM) of light failed to directly implement an interaction with chiral molecules, which remains poorly understood. Even with the enhancement of unique plasmonic nanoparticle aggregates, the helical dichroism (HD) is still at a small level of ~0.6%. Here, we experimentally report the direct observation of a giant HD at the level of ~120% by matching the scales of chiral microstructures and OAM beams. Our results reveal a strong interaction between OAM beams and chiral microstructures in terms of their distinct reflectance, resulting in sign-opposite HD values to distinguish their chirality. Such unique HD phenomenon is investigated experimentally under various diameters and helical pitches of chiral structures, showing the robust performance. This HD technique can widely extend the responding areas of chiral spectroscopy in biology, material science and nanotechnology.

physics.optics↗

arXiv2018

Data Acquisition Software for CBM-TOF super module quality control

The time-of-flight (TOF) system in the Compressed Baryonic Matter (CBM) experiment is composed of super modules based on multi-gap Resistive Plate Chambers (MRPC) for high-denseness, high-resolution time measurement. In order to evaluate the quality of detectors during the mass production, a distributed data readout system is developed to meet with the high data rate of 6.4Gbps, and a related data acquisition (DAQ) software is implemented under Linux operating system to test and verify the feasibility of the distributed data readout method. In this paper, the DAQ software is focused on data collection, event building, status monitoring and system controlling. Laboratory tests confirmed the function of the DAQ software and show that the overall data transfer rate of a single data transmission path can reach up to about 550Mbps which already meet the demand.

physics.ins-det↗

arXiv2016

Three-dimensional chiral microstructures fabricated by structured optical vortices in isotropic material

Optical vortices, as a kind of structured beam with helical phase wavefronts and doughnut shape intensity distribution, have been used for fabricating chiral structures in metal and spiral patterns in anisotropic polarization-dependent azobenzene polymer. However, in isotropic polymer, the fabricated microstructures are typically confined to non-chiral cylindrical geometry due to two-dimensional doughnut intensity profile of optical vortices. Here we develop a powerful strategy for realizing chiral microstructures in isotropic material by coaxial interference of a vortex beam and a plane wave, which produces three-dimensional (3D) spiral optical fields. This coaxial interference beams are creatively produced by designing the contrivable holograms consisting of azimuthal phase and equiphase loaded on liquid-crystal spatial light modulator. Then, in isotropic polymer, 3D chiral microstructures are achieved under illumination of the coaxial interference femtosecond laser beams with their chirality controlled by the topological charge. Our further investigation reveals that the spiral lobes and chirality are caused by the interfering patterns and helical phase wavefronts, respectively. This technique is simple, stable, and easy-operation, and offers broad applications in optical tweezers, optical communications and fast metamaterial fabrication.

physics.optics↗

arXiv2014

A measurable counterpart to the optical concept of an object

The traditional optical concept for the object does not provide an experimental feasibility to speak for itself, due to the fact that no measuring instrument catches up with the fluctuation of light fields. Using the theory of coherence, we give it a measurable counterpart, and thus to give a satisfactory explanation of what the concept has said. To our knowledge it is the first time to valuate an object in optics in the terms of observable quantities. As a useful example, the applicability to obtain the full knowledge of an object under the partial coherent illuminations is suggested. This work hit the thought which had been advanced by E. Wolf that one measures the correlation function rather than the optical fields themselves. The suggested applicability is a supplementary to the recently found solution to the determination of phases of the diffracted beam.

physics.optics↗