Searcharxiv⌕ Search

arXiv subjects

Hong Zhu

Publications and source records attributed to Hong Zhu.

70 records · Page 4Linked to original sources
arXiv2021

Less Is Better: Unweighted Data Subsampling via Influence Function

In the time of Big Data, training complex models on large-scale data sets is challenging, making it appealing to reduce data volume for saving computation resources by subsampling. Most previous works in subsampling are weighted methods designed to help the performance of subset-model approach the full-set-model, hence the weighted methods have no chance to acquire a subset-model that is better than the full-set-model. However, we question that how can we achieve better model with less data? In this work, we propose a novel Unweighted Influence Data Subsampling (UIDS) method, and prove that the subset-model acquired through our method can outperform the full-set-model. Besides, we show that overly confident on a given test set for sampling is common in Influence-based subsampling methods, which can eventually cause our subset-model's failure in out-of-sample test. To mitigate it, we develop a probabilistic sampling scheme to control the worst-case risk over all distributions close to the empirical distribution. The experiment results demonstrate our methods superiority over existed subsampling methods in diverse tasks, such as text classification, image classification, click-through prediction, etc.

cs.LG↗
arXiv2021

Non-invasive Self-attention for Side Information Fusion in Sequential Recommendation

Sequential recommender systems aim to model users' evolving interests from their historical behaviors, and hence make customized time-relevant recommendations. Compared with traditional models, deep learning approaches such as CNN and RNN have achieved remarkable advancements in recommendation tasks. Recently, the BERT framework also emerges as a promising method, benefited from its self-attention mechanism in processing sequential data. However, one limitation of the original BERT framework is that it only considers one input source of the natural language tokens. It is still an open question to leverage various types of information under the BERT framework. Nonetheless, it is intuitively appealing to utilize other side information, such as item category or tag, for more comprehensive depictions and better recommendations. In our pilot experiments, we found naive approaches, which directly fuse types of side information into the item embeddings, usually bring very little or even negative effects. Therefore, in this paper, we propose the NOninVasive self-attention mechanism (NOVA) to leverage side information effectively under the BERT framework. NOVA makes use of side information to generate better attention distribution, rather than directly altering the item embedding, which may cause information overwhelming. We validate the NOVA-BERT model on both public and commercial datasets, and our method can stably outperform the state-of-the-art models with negligible computational overheads.

cs.IR↗
arXiv2020

Deep Layout of Custom-size Furniture through Multiple-domain Learning

In this paper, we propose a multiple-domain model for producing a custom-size furniture layout in the interior scene. This model is aimed to support professional interior designers to produce interior decoration solutions with custom-size furniture more quickly. The proposed model combines a deep layout module, a domain attention module, a dimensional domain transfer module, and a custom-size module in the end-end training. Compared with the prior work on scene synthesis, our proposed model enhances the ability of auto-layout of custom-size furniture in the interior room. We conduct our experiments on a real-world interior layout dataset that contains $710,700$ designs from professional designers. Our numerical results demonstrate that the proposed model yields higher-quality layouts of custom-size furniture in comparison with the state-of-art model.

cs.CV↗
arXiv2020

End-to-end Generative Floor-plan and Layout with Attributes and Relation Graph

In this paper, we propose an end-end model for producing furniture layout for interior scene synthesis from the random vector. This proposed model is aimed to support professional interior designers to produce the interior decoration solutions more quickly. The proposed model combines a conditional floor-plan module of the room, a conditional graphical floor-plan module of the room and a conditional layout module. As compared with the prior work on scene synthesis, our proposed three modules enhance the ability of auto-layout generation given the dimensional category of the room. We conduct our experiments on the proposed real-world interior layout dataset that contains $191208$ designs from the professional designers. Our numerical results demonstrate that the proposed model yields higher-quality layouts in comparison with the state-of-the-art model. The dataset and code are released \href{https://github.com/CODE-SUBMIT/dataset3}{Dataset,Code}

cs.CV↗
arXiv2020

Structural Plan of Indoor Scenes with Personalized Preferences

In this paper, we propose an assistive model that supports professional interior designers to produce industrial interior decoration solutions and to meet the personalized preferences of the property owners. The proposed model is able to automatically produce the layout of objects of a particular indoor scene according to property owners' preferences. In particular, the model consists of the extraction of abstract graph, conditional graph generation, and conditional scene instantiation. We provide an interior layout dataset that contains real-world 11000 designs from professional designers. Our numerical results on the dataset demonstrate the effectiveness of the proposed model compared with the state-of-art methods.

cs.CV↗
arXiv2020

Adversarial Model for Rotated Indoor Scenes Planning

In this paper, we propose an adversarial model for producing furniture layout for interior scene synthesis when the interior room is rotated. The proposed model combines a conditional adversarial network, a rotation module, a mode module, and a rotation discriminator module. As compared with the prior work on scene synthesis, our proposed three modules enhance the ability of auto-layout generation and reduce the mode collapse during the rotation of the interior room. We conduct our experiments on a proposed real-world interior layout dataset that contains 14400 designs from the professional designers. Our numerical results demonstrate that the proposed model yields higher-quality layouts for four types of rooms, including the bedroom, the bathroom, the study room, and the tatami room.

cs.CV↗
arXiv2020

Hyper-Parameter Optimization: A Review of Algorithms and Applications

Since deep neural networks were developed, they have made huge contributions to everyday lives. Machine learning provides more rational advice than humans are capable of in almost every aspect of daily life. However, despite this achievement, the design and training of neural networks are still challenging and unpredictable procedures. To lower the technical thresholds for common users, automated hyper-parameter optimization (HPO) has become a popular topic in both academic and industrial areas. This paper provides a review of the most essential topics on HPO. The first section introduces the key hyper-parameters related to model training and structure, and discusses their importance and methods to define the value range. Then, the research focuses on major optimization algorithms and their applicability, covering their efficiency and accuracy especially for deep learning networks. This study next reviews major services and toolkits for HPO, comparing their support for state-of-the-art searching algorithms, feasibility with major deep learning frameworks, and extensibility for new modules designed by users. The paper concludes with problems that exist when HPO is applied to deep learning, a comparison between optimization algorithms, and prominent approaches for model evaluation with limited computational resources.

cs.LG↗
arXiv2019

Morphy: A Datamorphic Software Test Automation Tool

This paper presents an automated tool called Morphy for datamorphic testing. It classifies software test artefacts into test entities and test morphisms, which are mappings on testing entities. In addition to datamorphisms, metamorphisms and seed test case makers, Morphy also employs a set of other test morphisms including test case metrics and filters, test set metrics and filters, test result analysers and test executers to realise test automation. In particular, basic testing activities can be automated by invoking test morphisms. Test strategies can be realised as complex combinations of test morphisms. Test processes can be automated by recording, editing and playing test scripts that invoke test morphisms and strategies. Three types of test strategies have been implemented in Morphy: datamorphism combination strategies, cluster border exploration strategies and strategies for test set optimisation via genetic algorithms. This paper focuses on the datamorphism combination strategies by giving their definitions and implementation algorithms. The paper also illustrates their uses for testing both traditional software and AI applications with three case studies.

cs.SE↗
arXiv2019

Datamorphic Testing: A Methodology for Testing AI Applications

With the rapid growth of the applications of machine learning (ML) and other artificial intelligence (AI) techniques, adequate testing has become a necessity to ensure their quality. This paper identifies the characteristics of AI applications that distinguish them from traditional software, and analyses the main difficulties in applying existing testing methods. Based on this analysis, we propose a new method called datamorphic testing and illustrate the method with an example of testing face recognition applications. We also report an experiment with four real industrial application systems of face recognition to validate the proposed approach.

cs.SE↗
arXiv2019

Anion charge-lattice volume dependent Li ion migration in compounds with the face-centered cubic anion frameworks

The proper design principles are essential for the efficient development of superionic conductors. However, the existing design principles are mainly proposed from the perspective of crystal structures. In this work, the face-centered cubic (fcc) anion frameworks were creatively constructed to study the effects of anion charge and lattice volume on the stability of lithium ion occupation and lithium ion migration. Both the large negative anion charges and large lattice volumes would increase the relative stabilities of lithium-anion tetrahedron, and make Li ions prefer to occupy the tetrahedral sites. For a tetrahedral Li ion migration to its adjacent tetrahedral site through an octahedral transition state, the smaller the negative anion charge is, the lower the lithium ion migration barrier will be. While for an octahedral Li ion migration to its adjacent octahedral site through a tetrahedral transition state, the larger negative anion charge is, the lower the lithium ion migration barrier will be. New design principles for developing superionic conductors with the fcc anion framework were proposed. Low Li ion migration barriers would be achieved by adjusting the non-lithium elements within the same crystal structure framework to obtain the desired electronegativity difference between the anion element and non-lithium cation element.

physics.app-ph↗
arXiv2019

Seeing isn't Believing: Practical Adversarial Attack Against Object Detectors

In this paper, we presented systematic solutions to build robust and practical AEs against real world object detectors. Particularly, for Hiding Attack (HA), we proposed the feature-interference reinforcement (FIR) method and the enhanced realistic constraints generation (ERG) to enhance robustness, and for Appearing Attack (AA), we proposed the nested-AE, which combines two AEs together to attack object detectors in both long and short distance. We also designed diverse styles of AEs to make AA more surreptitious. Evaluation results show that our AEs can attack the state-of-the-art real-time object detectors (i.e., YOLO V3 and faster-RCNN) at the success rate up to 92.4% with varying distance from 1m to 25m and angles from -60° to 60°. Our AEs are also demonstrated to be highly transferable, capable of attacking another three state-of-the-art black-box models with high success rate.

cs.CV↗
arXiv2015

Profitability of simple technical trading rules of Chinese stock exchange indexes

Although technical trading rules have been widely used by practitioners in financial markets, their profitability still remains controversial. We here investigate the profitability of moving average (MA) and trading range break (TRB) rules by using the Shanghai Stock Exchange Composite Index (SHCI) from May 21, 1992 through December 31, 2013 and Shenzhen Stock Exchange Composite Index (SZCI) from April 3, 1991 through December 31, 2013. The $t$-test is adopted to check whether the mean returns which are conditioned on the trading signals are significantly different from unconditioned returns and whether the mean returns conditioned on the buy signals are significantly different from the mean returns conditioned on the sell signals. We find that TRB rules outperform MA rules and short-term variable moving average (VMA) rules outperform long-term VMA rules. By applying White's Reality Check test and accounting for the data snooping effects, we find that the best trading rule outperforms the buy-and-hold strategy when transaction costs are not taken into consideration. Once transaction costs are included, trading profits will be eliminated completely. Our analysis suggests that simple trading rules like MA and TRB cannot beat the standard buy-and-hold strategy for the Chinese stock exchange indexes.

q-fin.TR↗
arXiv2004

Quantum m-out-of-n Oblivious Transfer

In the m-out-of-n oblivious transfer (OT) model, one party Alice sends n bits to another party Bob, Bob can get only m bits from the n bits. However, Alice cannot know which m bits Bob received. Y.Mu[MJV02]} and Naor[Naor01] presented classical m-out-of-n oblivious transfer based on discrete logarithm. As the work of Shor [Shor94], the discrete logarithm can be solved in polynomial time by quantum computers, so such OTs are unsafe to the quantum computer. In this paper, we construct a quantum m-out-of-n OT (QOT) scheme based on the transmission of polarized light and show that the scheme is robust to general attacks, i.e. the QOT scheme satisfies statistical correctness and statistical privacy.

cs.CR↗