arXiv subjects

Ke Li

Publications and source records attributed to Ke Li.

At least 415 records · Page 23Linked to original sources

arXiv2019

The Mass, Fake News, and Cognition Security

The wide spread of fake news in social networks is posing threats to social stability, economic development and political democracy etc. Numerous studies have explored the effective detection approaches of online fake news, while few works study the intrinsic propagation and cognition mechanisms of fake news. Since the development of cognitive science paves a promising way for the prevention of fake news, we present a new research area called Cognition Security (CogSec), which studies the potential impacts of fake news to human cognition, ranging from misperception, untrusted knowledge acquisition, targeted opinion/attitude formation, to biased decision making, and investigates the effective ways for fake news debunking. CogSec is a multidisciplinary research field that leverages knowledge from social science, psychology, cognition science, neuroscience, AI and computer science. We first propose related definitions to characterize CogSec and review the literature history. We further investigate the key research challenges and techniques of CogSec, including human-content cognition mechanism, social influence and opinion diffusion, fake news detection and malicious bot detection. Finally, we summarize the open issues and future research directions, such as early detection of fake news, explainable fake news debunking, social contagion and diffusion models of fake news, and so on.

cs.CY↗

arXiv2019

Visualisation of Pareto Front Approximation: A Short Survey and Empirical Comparisons

Visualisation is an effective way to facilitate the analysis and understanding of multivariate data. In the context of multi-objective optimisation, comparing to quantitative performance metrics, visualisation is, in principle, able to provide a decision maker better insights about Pareto front approximation sets (e.g. the distribution of solutions, the geometric characteristics of Pareto front approximation) thus to facilitate the decision-making (e.g. the exploration of trade-off relationship, the knee region or region of interest). In this paper, we overview some currently prevalent visualisation techniques according to the way how data is represented. To have a better understanding of the pros and cons of different visualisation techniques, we empirically compare six representative visualisation techniques for the exploratory analysis of different Pareto front approximation sets obtained by four state-of-the-art evolutionary multi-objective optimisation algorithms on the classic DTLZ benchmark test problems. From the empirical results, we find that visual comparisons also follow the \textit{No-Free-Lunch} theorem where no single visualisation technique is able to provide a comprehensive understanding of the characteristics of a Pareto front approximation set. In other words, a specific type of visualisation technique is only good at exploring a particular aspect of the data.

cs.NE↗

arXiv2019

Which Surrogate Works for Empirical Performance Modelling? A Case Study with Differential Evolution

It is not uncommon that meta-heuristic algorithms contain some intrinsic parameters, the optimal configuration of which is crucial for achieving their peak performance. However, evaluating the effectiveness of a configuration is expensive, as it involves many costly runs of the target algorithm. Perhaps surprisingly, it is possible to build a cheap-to-evaluate surrogate that models the algorithm's empirical performance as a function of its parameters. Such surrogates constitute an important building block for understanding algorithm performance, algorithm portfolio/selection, and the automatic algorithm configuration. In principle, many off-the-shelf machine learning techniques can be used to build surrogates. In this paper, we take the differential evolution (DE) as the baseline algorithm for proof-of-concept study. Regression models are trained to model the DE's empirical performance given a parameter configuration. In particular, we evaluate and compare four popular regression algorithms both in terms of how well they predict the empirical performance with respect to a particular parameter configuration, and also how well they approximate the parameter versus the empirical performance landscapes.

cs.NE↗

arXiv2019

Trajectory Normalized Gradients for Distributed Optimization

Recently, researchers proposed various low-precision gradient compression, for efficient communication in large-scale distributed optimization. Based on these work, we try to reduce the communication complexity from a new direction. We pursue an ideal bijective mapping between two spaces of gradient distribution, so that the mapped gradient carries greater information entropy after the compression. In our setting, all servers should share a reference gradient in advance, and they communicate via the normalized gradients, which are the subtraction or quotient, between current gradients and the reference. To obtain a reference vector that yields a stronger signal-to-noise ratio, dynamically in each iteration, we extract and fuse information from the past trajectory in hindsight, and search for an optimal reference for compression. We name this to be the trajectory-based normalized gradients (TNG). It bridges the research from different societies, like coding, optimization, systems, and learning. It is easy to implement and can universally combine with existing algorithms. Our experiments on benchmarking hard non-convex functions, convex problems like logistic regression demonstrate that TNG is more compression-efficient for communication of distributed optimization of general functions.

cs.LG↗

arXiv2019

Speaker Adaptation for End-to-End CTC Models

We propose two approaches for speaker adaptation in end-to-end (E2E) automatic speech recognition systems. One is Kullback-Leibler divergence (KLD) regularization and the other is multi-task learning (MTL). Both approaches aim to address the data sparsity especially output target sparsity issue of speaker adaptation in E2E systems. The KLD regularization adapts a model by forcing the output distribution from the adapted model to be close to the unadapted one. The MTL utilizes a jointly trained auxiliary task to improve the performance of the main task. We investigated our approaches on E2E connectionist temporal classification (CTC) models with three different types of output units. Experiments on the Microsoft short message dictation task demonstrated that MTL outperforms KLD regularization. In particular, the MTL adaptation obtained 8.8\% and 4.0\% relative word error rate reductions (WERRs) for supervised and unsupervised adaptations for the word CTC model, and 9.6% and 3.8% relative WERRs for the mix-unit CTC model, respectively.

cs.CL↗

arXiv2018

Are All Training Examples Created Equal? An Empirical Study

Modern computer vision algorithms often rely on very large training datasets. However, it is conceivable that a carefully selected subsample of the dataset is sufficient for training. In this paper, we propose a gradient-based importance measure that we use to empirically analyze relative importance of training images in four datasets of varying complexity. We find that in some cases, a small subsample is indeed sufficient for training. For other datasets, however, the relative differences in importance are negligible. These results have important implications for active learning on deep networks. Additionally, our analysis method can be used as a general tool to better understand diversity of training examples in datasets.

cs.LG↗

arXiv2018

On the Implicit Assumptions of GANs

Generative adversarial nets (GANs) have generated a lot of excitement. Despite their popularity, they exhibit a number of well-documented issues in practice, which apparently contradict theoretical guarantees. A number of enlightening papers have pointed out that these issues arise from unjustified assumptions that are commonly made, but the message seems to have been lost amid the optimism of recent years. We believe the identified problems deserve more attention, and highlight the implications on both the properties of GANs and the trajectory of research on probabilistic models. We recently proposed an alternative method that sidesteps these problems.

cs.LG↗

arXiv2018

Implicit Maximum Likelihood Estimation

Implicit probabilistic models are models defined naturally in terms of a sampling procedure and often induces a likelihood function that cannot be expressed explicitly. We develop a simple method for estimating parameters in implicit models that does not require knowledge of the form of the likelihood function or any derived quantities, but can be shown to be equivalent to maximizing likelihood under some conditions. Our result holds in the non-asymptotic parametric setting, where both the capacity of the model and the number of data examples are finite. We also demonstrate encouraging experimental results.

cs.LG↗

arXiv2018

Super-Resolution via Conditional Implicit Maximum Likelihood Estimation

Single-image super-resolution (SISR) is a canonical problem with diverse applications. Leading methods like SRGAN produce images that contain various artifacts, such as high-frequency noise, hallucinated colours and shape distortions, which adversely affect the realism of the result. In this paper, we propose an alternative approach based on an extension of the method of Implicit Maximum Likelihood Estimation (IMLE). We demonstrate greater effectiveness at noise reduction and preservation of the original colours and shapes, yielding more realistic super-resolved images.

cs.LG↗

arXiv2018

Interactive Decomposition Multi-Objective Optimization via Progressively Learned Value Functions

Decomposition has become an increasingly popular technique for evolutionary multi-objective optimization (EMO). A decomposition-based EMO algorithm is usually designed to approximate a whole Pareto-optimal front (PF). However, in practice, the decision maker (DM) might only be interested in her/his region of interest (ROI), i.e., a part of the PF. Solutions outside that might be useless or even noisy to the decision-making procedure. Furthermore, there is no guarantee to find the preferred solutions when tackling many-objective problems. This paper develops an interactive framework for the decomposition-based EMO algorithm to lead a DM to the preferred solutions of her/his choice. It consists of three modules, i.e., consultation, preference elicitation and optimization. Specifically, after every several generations, the DM is asked to score a few candidate solutions in a consultation session. Thereafter, an approximated value function, which models the DM's preference information, is progressively learned from the DM's behavior. In the preference elicitation session, the preference information learned in the consultation module is translated into the form that can be used in a decomposition-based EMO algorithm, i.e., a set of reference points that are biased toward to the ROI. The optimization module, which can be any decomposition-based EMO algorithm in principle, utilizes the biased reference points to direct its search process. Extensive experiments on benchmark problems with three to ten objectives fully demonstrate the effectiveness of our proposed method for finding the DM's preferred solutions.

cs.NE↗

arXiv2018

Universal Perceptual Grouping

In this work we aim to develop a universal sketch grouper. That is, a grouper that can be applied to sketches of any category in any domain to group constituent strokes/segments into semantically meaningful object parts. The first obstacle to this goal is the lack of large-scale datasets with grouping annotation. To overcome this, we contribute the largest sketch perceptual grouping (SPG) dataset to date, consisting of 20,000 unique sketches evenly distributed over 25 object categories. Furthermore, we propose a novel deep universal perceptual grouping model. The model is learned with both generative and discriminative losses. The generative losses improve the generalisation ability of the model to unseen object categories and datasets. The discriminative losses include a local grouping loss and a novel global grouping loss to enforce global grouping consistency. We show that the proposed model significantly outperforms the state-of-the-art groupers. Further, we show that our grouper is useful for a number of sketch analysis tasks including sketch synthesis and fine-grained sketch-based image retrieval (FG-SBIR).

cs.CV↗

arXiv2018

Robust Group Comparison Using Non-Parametric Block-Based Statistics

Voxel-based analysis methods localize brain structural differences by performing voxel-wise statistical comparisons on two groups of images aligned to a common space. This procedure requires highly accurate registration as well as a sufficiently large dataset. However, in practice, the registration algorithms are not perfect due to noise, artifacts, and complex structural variations. The sample size is also limited due to low disease prevalence, recruitment difficulties, and demographic matching issues. To address these issues, in this paper, we propose a method, called block-based statistic (BBS), for robust group comparison. BBS consists of two major components: Block matching and permutation test. Specifically, based on two group of images aligned to a common space, we first perform block matching so that structural misalignments can be corrected. Then, based on results given by block matching, we conduct robust non-parametric statistical inference based on permutation test. Extensive experiments were performed on synthetic data and the real diffusion MR data of mild cognitive impairment patients. The experimental results indicate that BBS significantly improves statistical power, notwithstanding the small sample size.

stat.AP↗

arXiv2018

FEMOSAA: Feature Guided and Knee Driven Multi-Objective Optimization for Self-Adaptive Software

Self-adaptive software (SAS) can reconfigure itself to adapt to the changing environment at runtime, aiming for continually optimizing conflicted non-functional objectives, e.g., response time, energy consumption, throughput and cost etc. In this paper, we present Feature guided and knEe driven Multi-Objective optimization for Self-Adaptive softwAre (FEMOSAA), a novel framework that automatically synergizes the feature model and Multi-Objective Evolutionary Algorithm (MOEA), to optimize SAS at runtime. FEMOSAA operates in two phases: at design time, FEMOSAA automatically transposes the engineers' design of SAS, expressed as a feature model, to fit the MOEA, creating new chromosome representation and reproduction operators. At runtime, FEMOSAA utilizes the feature model as domain knowledge to guide the search and further extend the MOEA, providing a larger chance for finding better solutions. In addition, we have designed a new method to search for the knee solutions, which can achieve a balanced trade-off. We comprehensively evaluated FEMOSAA on two running SAS: one is a highly complex SAS with various adaptable real-world software under the realistic workload trace, another is a service-oriented SAS that can be dynamically composed from services. In particular, we compared the effectiveness and overhead of FEMOSAA against four of its variants and three other search-based frameworks for SAS under various scenarios, including three commonly applied MOEAs, two workload patterns and diverse conflicting quality objectives. The results reveal the effectiveness of FEMOSAA and its superiority over the others with high statistical significance and non-trivial effect sizes.

cs.SE↗

arXiv2018

Squashed entanglement, k-extendibility, quantum Markov chains, and recovery maps

Squashed entanglement [Christandl and Winter, J. Math. Phys. 45(3):829-840 (2004)] is a monogamous entanglement measure, which implies that highly extendible states have small value of the squashed entanglement. Here, invoking a recent inequality for the quantum conditional mutual information [Fawzi and Renner, Commun. Math. Phys. 340(2):575-611 (2015)] greatly extended and simplified in various work since, we show the converse, that a small value of squashed entanglement implies that the state is close to a highly extendible state. As a corollary, we establish an alternative proof of the faithfulness of squashed entanglement [Brandao, Christandl and Yard, Commun. Math. Phys. 306:805-830 (2011)]. We briefly discuss the previous and subsequent history of the Fawzi-Renner bound and related conjectures, and close by advertising a potentially far-reaching generalization to universal and functorial recovery maps for the monotonicity of the relative entropy.

quant-ph↗

arXiv2017

Learning to Optimize Neural Nets

Learning to Optimize is a recently proposed framework for learning optimization algorithms using reinforcement learning. In this paper, we explore learning an optimization algorithm for training shallow neural nets. Such high-dimensional stochastic optimization problems present interesting challenges for existing reinforcement learning algorithms. We develop an extension that is suited to learning optimization algorithms in this setting and demonstrate that the learned optimization algorithm consistently outperforms other known optimization algorithms even on unseen tasks and is robust to changes in stochasticity of gradients and the neural net architecture. More specifically, we show that an optimization algorithm trained with the proposed method on the problem of training a neural net on MNIST generalizes to the problems of training neural nets on the Toronto Faces Dataset, CIFAR-10 and CIFAR-100.

cs.LG↗

arXiv2017

Two-Archive Evolutionary Algorithm for Constrained Multi-Objective Optimization

When solving constrained multi-objective optimization problems, an important issue is how to balance convergence, diversity and feasibility simultaneously. To address this issue, this paper proposes a parameter-free constraint handling technique, two-archive evolutionary algorithm, for constrained multi-objective optimization. It maintains two co-evolving populations simultaneously: one, denoted as convergence archive, is the driving force to push the population toward the Pareto front; the other one, denoted as diversity archive, mainly tends to maintain the population diversity. In particular, to complement the behavior of the convergence archive and provide as much diversified information as possible, the diversity archive aims at exploring areas under-exploited by the convergence archive including the infeasible regions. To leverage the complementary effects of both archives, we develop a restricted mating selection mechanism that adaptively chooses appropriate mating parents from them according to their evolution status. Comprehensive experiments on a series of benchmark problems and a real-world case study fully demonstrate the competitiveness of our proposed algorithm, comparing to five state-of-the-art constrained evolutionary multi-objective optimizers.

cs.NE↗

arXiv2017

Uncertainties of the $B\to D$ transition form factor from the $D$-Meson Leading-Twist Distribution Amplitude

The $B\to D$ transition form factor (TFF) $f^{B\to D}_+(q^2)$ is determined mainly by the $D$-meson leading-twist distribution amplitude (DA) , $ϕ_{2;D}$, if the proper chiral current correlation function is adopted within the light-cone QCD sum rules. It is therefore significant to make a comprehensive study of DA $ϕ_{2;D}$ and its impact on $f^{B\to D}_+(q^2)$. In this paper, we calculate the moments of $ϕ_{2;D}$ with the QCD sum rules under the framework of the background field theory. New sum rules for the leading-twist DA moments $\left<ξ^n\right>_D$ up to fourth order and up to dimension-six condensates are presented. At the scale $μ= 2 \rm GeV$, the values of the first four moments are: $\left<ξ^1\right>_D = -0.418^{+0.021}_{-0.022}$, $\left<ξ^2\right>_D = 0.289^{+0.023}_{-0.022}$, $\left<ξ^3\right>_D = -0.178 \pm 0.010$ and $\left<ξ^4\right>_D = 0.142^{+0.013}_{-0.012}$. Basing on the values of $\left<ξ^n\right>_D(n=1,2,3,4)$, a better model of $ϕ_{2;D}$ is constructed. Applying this model for the TFF $f^{B\to D}_+(q^2)$ under the light cone sum rules, we obtain $f^{B\to D}_+(0) = 0.673^{+0.038}_{-0.041}$ and $f^{B\to D}_+(q^2_{\rm max}) = 1.124^{+0.053}_{-0.058}$. The uncertainty of $f^{B\to D}_+(q^2)$ from $ϕ_{2;D}$ is estimated and we find its impact should be taken into account, especially in low and central energy region. The branching ratio $\mathcal{B}(B\to Dl\barν_l)$ is calculated, which is consistent with experimental data.

hep-ph↗

arXiv2017

Fast k-Nearest Neighbour Search via Prioritized DCI

Most exact methods for k-nearest neighbour search suffer from the curse of dimensionality; that is, their query times exhibit exponential dependence on either the ambient or the intrinsic dimensionality. Dynamic Continuous Indexing (DCI) offers a promising way of circumventing the curse and successfully reduces the dependence of query time on intrinsic dimensionality from exponential to sublinear. In this paper, we propose a variant of DCI, which we call Prioritized DCI, and show a remarkable improvement in the dependence of query time on intrinsic dimensionality. In particular, a linear increase in intrinsic dimensionality, or equivalently, an exponential increase in the number of points near a query, can be mostly counteracted with just a linear increase in space. We also demonstrate empirically that Prioritized DCI significantly outperforms prior methods. In particular, relative to Locality-Sensitive Hashing (LSH), Prioritized DCI reduces the number of distance evaluations by a factor of 14 to 116 and the memory consumption by a factor of 21.

cs.LG↗