arXiv subjects

Ke Liu

Publications and source records attributed to Ke Liu.

At least 127 records · Page 7Linked to original sources

arXiv2022

Supervised Deep Hashing for High-dimensional and Heterogeneous Case-based Reasoning

Case-based Reasoning (CBR) on high-dimensional and heterogeneous data is a trending yet challenging and computationally expensive task in the real world. A promising approach is to obtain low-dimensional hash codes representing cases and perform a similarity retrieval of cases in Hamming space. However, previous methods based on data-independent hashing rely on random projections or manual construction, inapplicable to address specific data issues (e.g., high-dimensionality and heterogeneity) due to their insensitivity to data characteristics. To address these issues, this work introduces a novel deep hashing network to learn similarity-preserving compact hash codes for efficient case retrieval and proposes a deep-hashing-enabled CBR model HeCBR. Specifically, we introduce position embedding to represent heterogeneous features and utilize a multilinear interaction layer to obtain case embeddings, which effectively filtrates zero-valued features to tackle high-dimensionality and sparsity and captures inter-feature couplings. Then, we feed the case embeddings into fully-connected layers, and subsequently a hash layer generates hash codes with a quantization regularizer to control the quantization loss during relaxation. To cater to incremental learning of CBR, we further propose an adaptive learning strategy to update the hash function. Extensive experiments on public datasets show that HeCBR greatly reduces storage and significantly accelerates case retrieval. HeCBR achieves desirable performance compared with the state-of-the-art CBR methods and performs significantly better than hashing-based CBR methods in classification.

cs.IR↗

arXiv2022

BashExplainer: Retrieval-Augmented Bash Code Comment Generation based on Fine-tuned CodeBERT

Developers use shell commands for many tasks, such as file system management, network control, and process management. Bash is one of the most commonly used shells and plays an important role in Linux system development and maintenance. Due to the language flexibility of Bash code, developers who are not familiar with Bash often have difficulty understanding the purpose and functionality of Bash code. In this study, we study Bash code comment generation problem and proposed an automatic method BashExplainer based on two-stage training strategy. In the first stage, we train a Bash encoder by fine-tuning CodeBERT on our constructed Bash code corpus. In the second stage, we first retrieve the most similar code from the code repository for the target code based on semantic and lexical similarity. Then we use the trained Bash encoder to generate two vector representations. Finally, we fuse these two vector representations via the fusion layer and generate the code comment through the decoder. To show the competitiveness of our proposed method, we construct a high-quality corpus by combining the corpus shared in the previous NL2Bash study and the corpus shared in the NLC2CMD competition. This corpus contains 10,592 Bash codes and corresponding comments. Then we selected ten baselines from previous studies on automatic code comment generation, which cover information retrieval methods, deep learning methods, and hybrid methods.

cs.SE↗

arXiv2022

High-quality femtosecond laser surface micro/nano-structuring assisted by a thin frost layer

Femtosecond laser ablation has been demonstrated to be a versatile tool to produce micro/nanoscale features with high precision and accuracy. However, the use of high laser fluence to increase the ablation efficiency usually results in unwanted effects, such as redeposition of debris, formation of recast layer and heat-affected zone in or around the ablation craters. Here we circumvent this limitation by exploiting a thin frost layer with a thickness of tens of microns, which can be directly formed by the condensation of water vapor from the air onto the exposed surface whose temperature is below the freezing point. When femtosecond laser beam is focused onto the target surface covered with a thin frost layer, only the local frost layer around the laser-irradiated spot melts into water, helping to boost ablation efficiency, suppress the recast layer and reduce the heat-affect zone, while the remaining frost layer can prevent ablation debris from adhering to the target surface. By this frost-assisted strategy, high-quality surface micro/nano-structures are successfully achieved on both plane and curved surfaces at high laser fluences, and the mechanism behind the formation of high-spatial-frequency (HSF) laser induced periodic surface structures (LIPSSs) on silicon is discussed.

physics.optics↗

arXiv2022

SOTitle: A Transformer-based Post Title Generation Approach for Stack Overflow

On Stack Overflow, developers can not only browse question posts to solve their programming problems but also gain expertise from the question posts to help improve their programming skills. Therefore, improving the quality of question posts in Stack Overflow has attracted the wide attention of researchers. A concise and precise title can play an important role in helping developers understand the key information of the question post, which can improve the post quality. However, the quality of the generated title is not high due to the lack of professional knowledge related to their questions or the poor presentation ability of developers. A previous study aimed to automatically generate the title by analyzing the code snippets in the question post. However, this study ignored the useful information in the corresponding problem description. Therefore, we propose an approach SOTitle for automatic post title generation by leveraging the code snippets and the problem description in the question post (i.e., the multi-modal input). SOTitle follows the Transformer structure, which can effectively capture long-term dependencies through a multi-head attention mechanism. To verify the effectiveness of SOTitle, we construct a large-scale high-quality corpus from Stack Overflow, which includes 1,168,257 high-quality question posts for four popular programming languages. Experimental results show that SOTitle can significantly outperform six state-of-the-art baselines in both automatic evaluation and human evaluation. To encourage follow-up studies, we make our corpus and approach publicly available

cs.SE↗

arXiv2022

Transient behaviour of electrovortex flow in a cylindrical container

This study is a continuation of the combined experimental and numerical investigation [1] of the flow of the eutectic GaInSn alloy inside a cylindrical vessel exposed to a constant electrical current. The emerging electrovortex flow driven by the interaction of the current, which is applied through a tapered electrode, with its own magnetic field might have both detrimental and advantageous effects in liquid metal batteries. While the former work [1] was mainly concerned with time-averaged results, this paper focuses on the transient behaviour of the electrovortex flow which becomes most relevant under the influence of an external axial field. The additional Lorentz force generated by the interaction of the imposed current with the vertical component of the geomagnetic field bz drives the ordinary electrovortex jet flow into a swirling motion. Velocity distributions and motion characteristics, such as spiral streamlines and shortened and irregularly swinging jet regions, are investigated. The mechanism is analysed in detail for bz = 25.5 μT. The maximum angular velocity of the rotating jet is basically linearly dependent on bz, at least for the values studied here. A good agreement between the transient simulation and the experimental result is shown.

physics.flu-dyn↗

arXiv2021

Mechanical Cloak via Data-Driven Aperiodic Metamaterial Design

Mechanical cloaks are materials engineered to manipulate the elastic response around objects to make them indistinguishable from their homogeneous surroundings. Typically, methods based on material-parameter transformations are used to design optical, thermal and electric cloaks. However, they are not applicable in designing mechanical cloaks, since continuum-mechanics equations are not form-invariant under general coordinate transformations. As a result, existing design methods for mechanical cloaks have so far been limited to a narrow selection of voids with simple shapes. To address this challenge, we present a systematic, data-driven design approach to create mechanical cloaks composed of aperiodic metamaterials using a large pre-computed unit cell database. Our method is flexible to allow the design of cloaks with various boundary conditions, multiple loadings, different shapes and numbers of voids, and different homogeneous surroundings. It enables a concurrent optimization of both topology and properties distribution of the cloak. Compared to conventional fixed-shape solutions, this results in an overall better cloaking performance, and offers unparalleled versatility. Experimental measurements on 3D-printed structures further confirm the validity of the proposed approach. Our research illustrates the benefits of data-driven approaches in quickly responding to new design scenarios and resolving the computational challenge associated with multiscale designs of functional structures. It could be generalized to accommodate other applications that require heterogeneous property distribution, such as soft robots and implants design.

physics.app-ph↗

arXiv2021

The treewidth of 2-section of hypergraphs

Let $H=(V,F)$ be a simple hypergraph without loops. $H$ is called linear if $|f\cap g|\le 1$ for any $f,g\in F$ with $f\not=g$. The $2$-section of $H$, denoted by $[H]_2$, is a graph with $V([H]_2)=V$ and for any $ u,v\in V([H]_2)$, $uv\in E([H]_2)$ if and only if there is $ f\in F$ such that $u,v\in f$. The treewidth of a graph is an important invariant in structural and algorithmic graph theory. In this paper, we consider the treewidth of the $2$-section of a linear hypergraph. We will use the minimum degree, maximum degree, anti-rank and average rank of a linear hypergraph to determine the upper and lower bounds of the treewidth of its $2$-section. Since for any graph $G$, there is a linear hypergraph $H$ such that $[H]_2\cong G$, we provide a method to estimate the bound of treewidth of graph by the parameters of the hypergraph.

math.CO↗

arXiv2021

A Light Heterogeneous Graph Collaborative Filtering Model using Textual Information

Due to the development of graph neural networks, graph-based representation learning methods have made great progress in recommender systems. However, data sparsity is still a challenging problem that most graph-based recommendation methods are confronted with. Recent works try to address this problem by utilizing side information. In this paper, we exploit the relevant and easily accessible textual information by advanced natural language processing (NLP) models and propose a light RGCN-based (RGCN, relational graph convolutional network) collaborative filtering method on heterogeneous graphs. Specifically, to incorporate rich textual knowledge, we utilize a pre-trained NLP model to initialize the embeddings of text nodes. Afterward, by performing a simplified RGCN-based node information propagation on the constructed heterogeneous graph, the embeddings of users and items can be adjusted with textual knowledge, which effectively alleviates the negative effects of data sparsity. Moreover, the matching function used by most graph-based representation learning methods is the inner product, which is not appropriate for the obtained embeddings that contain complex semantics. We design a predictive network that combines graph-based representation learning with neural matching function learning, and demonstrate that this architecture can bring a significant performance improvement. Extensive experiments are conducted on three publicly available datasets, and the results verify the superior performance of our method over several baselines.

cs.IR↗

arXiv2021

Machine-Learned Phase Diagrams of Generalized Kitaev Honeycomb Magnets

We use a recently developed interpretable and unsupervised machine-learning method, the tensorial kernel support vector machine (TK-SVM), to investigate the low-temperature classical phase diagram of a generalized Heisenberg-Kitaev-$Γ$ ($J$-$K$-$Γ$) model on a honeycomb lattice. Aside from reproducing phases reported by previous quantum and classical studies, our machine finds a hitherto missed nested zigzag-stripy order and establishes the robustness of a recently identified modulated $S_3 \times Z_3$ phase, which emerges through the competition between the Kitaev and $Γ$ spin liquids, against Heisenberg interactions. The results imply that, in the restricted parameter space spanned by the three primary exchange interactions -- $J$, $K$, and $Γ$, the representative Kitaev material $α$-${\rm RuCl}_3$ lies close to the boundaries of several phases, including a simple ferromagnet, the unconventional $S_3 \times Z_3$ and nested zigzag-stripy magnets. A zigzag order is stabilized by a finite $Γ^{\prime}$ and/or $J_3$ term, whereas the four magnetic orders may compete in particular if $Γ^{\prime}$ is anti-ferromagnetic.

cond-mat.str-el↗

arXiv2021

Focusing on Persons: Colorizing Old Images Learning from Modern Historical Movies

In industry, there exist plenty of scenarios where old gray photos need to be automatically colored, such as video sites and archives. In this paper, we present the HistoryNet focusing on historical person's diverse high fidelity clothing colorization based on fine grained semantic understanding and prior. Colorization of historical persons is realistic and practical, however, existing methods do not perform well in the regards. In this paper, a HistoryNet including three parts, namely, classification, fine grained semantic parsing and colorization, is proposed. Classification sub-module supplies classifying of images according to the eras, nationalities and garment types; Parsing sub-network supplies the semantic for person contours, clothing and background in the image to achieve more accurate colorization of clothes and persons and prevent color overflow. In the training process, we integrate classification and semantic parsing features into the coloring generation network to improve colorization. Through the design of classification and parsing subnetwork, the accuracy of image colorization can be improved and the boundary of each part of image can be more clearly. Moreover, we also propose a novel Modern Historical Movies Dataset (MHMD) containing 1,353,166 images and 42 labels of eras, nationalities, and garment types for automatic colorization from 147 historical movies or TV series made in modern time. Various quantitative and qualitative comparisons demonstrate that our method outperforms the state-of-the-art colorization methods, especially on military uniforms, which has correct colors according to the historical literatures.

cs.CV↗

arXiv2021

ChemiRise: a data-driven retrosynthesis engine

We have developed an end-to-end, retrosynthesis system, named ChemiRise, that can propose complete retrosynthesis routes for organic compounds rapidly and reliably. The system was trained on a processed patent database of over 3 million organic reactions. Experimental reactions were atom-mapped, clustered, and extracted into reaction templates. We then trained a graph convolutional neural network-based one-step reaction proposer using template embeddings and developed a guiding algorithm on the directed acyclic graph (DAG) of chemical compounds to find the best candidate to explore. The atom-mapping algorithm and the one-step reaction proposer were benchmarked against previous studies and showed better results. The final product was demonstrated by retrosynthesis routes reviewed and rated by human experts, showing satisfying functionality and a potential productivity boost in real-life use cases.

physics.chem-ph↗

arXiv2021

Treewidth of the generalized Kneser graphs

Let $n$, $k$ and $t$ be integers with $1\leq t< k \leq n$. The \emph{generalized Kneser graph} $K(n,k,t)$ is a graph whose vertices are the $k$-subsets of a fixed $n$-set, where two $k$-subsets $A$ and $B$ are adjacent if $|A\cap B|<t$. The graph $K(n,k,1)$ is the well-known \emph{Kneser graph}. In 2014, Harvey and Wood determined the exact treewidth of the Kneser graphs for large $n$ with respect to $k$. In this paper, we give the exact treewidth of the generalized Kneser graphs for $t\geq2$ and large $n$ with respect to $k$ and $t$. In the special case when $t=k-1$, the graph $K(n,k,k-1)$ usually denoted by $\overline{J(n,k)}$ which is the complement of the Johnson graph $J(n,k)$. We give a more precise result for the exact value of the treewidth of $\overline{J(n,k)}$ for any $n$ and $k$.

math.CO↗

arXiv2021

Inferring Hidden Symmetries of Exotic Magnets from Detecting Explicit Order Parameters

An unconventional magnet may be mapped onto a simple ferromagnet by the existence of a high-symmetry point. Knowledge of conventional ferromagnetic systems may then be carried over to provide insight into more complex orders. Here we demonstrate how an unsupervised and interpretable machine-learning approach can be used to search for potential high-symmetry points in unconventional magnets without any prior knowledge of the system. The method is applied to the classical Heisenberg-Kitaev model on a honeycomb lattice, where our machine learns the transformations that manifest its hidden $O(3)$ symmetry, without using data of these high-symmetry points. Moreover, we clarify that, in contrast to the stripy and zigzag orders, a set of $D_2$ and $D_{2h}$ ordering matrices provides a more complete description of the magnetization in the Heisenberg-Kitaev model. In addition, our machine also learns the local constraints at the phase boundaries, which manifest a subdimensional symmetry. This paper highlights the importance of explicit order parameters to many-body spin systems and the property of interpretability for the physical application of machine-learning techniques.

physics.comp-ph↗

arXiv2021

ComFormer: Code Comment Generation via Transformer and Fusion Method-based Hybrid Code Representation

Developers often write low-quality code comments due to the lack of programming experience, which can reduce the efficiency of developers program comprehension. Therefore, developers hope that code comment generation tools can be developed to illustrate the functionality and purpose of the code. Recently, researchers mainly model this problem as the neural machine translation problem and tend to use deep learning-based methods. In this study, we propose a novel method ComFormer based on Transformer and fusion method-based hybrid code presentation. Moreover, to alleviate OOV (out-of-vocabulary) problem and speed up model training, we further utilize the Byte-BPE algorithm to split identifiers and Sim_SBT method to perform AST Traversal. We compare ComFormer with seven state-of-the-art baselines from code comment generation and neural machine translation domains. Comparison results show the competitiveness of ComFormer in terms of three performance measures. Moreover, we perform a human study to verify that ComFormer can generate high-quality comments.

cs.SE↗

arXiv2021

Semantic Segmentation by Improved Generative Adversarial Networks

While most existing segmentation methods usually combined the powerful feature extraction capabilities of CNNs with Conditional Random Fields (CRFs) post-processing, the result always limited by the fault of CRFs . Due to the notoriously slow calculation speeds and poor efficiency of CRFs, in recent years, CRFs post-processing has been gradually eliminated. In this paper, an improved Generative Adversarial Networks (GANs) for image semantic segmentation task (semantic segmentation by GANs, Seg-GAN) is proposed to facilitate further segmentation research. In addition, we introduce Convolutional CRFs (ConvCRFs) as an effective improvement solution for the image semantic segmentation task. Towards the goal of differentiating the segmentation results from the ground truth distribution and improving the details of the output images, the proposed discriminator network is specially designed in a full convolutional manner combined with cascaded ConvCRFs. Besides, the adversarial loss aggressively encourages the output image to be close to the distribution of the ground truth. Our method not only learns an end-to-end mapping from input image to corresponding output image, but also learns a loss function to train this mapping. The experiments show that our method achieves better performance than state-of-the-art methods.

cs.CV↗

arXiv2021

Molecular modeling with machine-learned universal potential functions

Molecular modeling is an important topic in drug discovery. Decades of research have led to the development of high quality scalable molecular force fields. In this paper, we show that neural networks can be used to train a universal approximator for energy potential functions. By incorporating a fully automated training process we have been able to train smooth, differentiable, and predictive potential functions on large-scale crystal structures. A variety of tests have also been performed to show the superiority and versatility of the machine-learned model.

q-bio.QM↗

arXiv2021

Revealing the Phase Diagram of Kitaev Materials by Machine Learning: Cooperation and Competition between Spin Liquids

Kitaev materials are promising materials for hosting quantum spin liquids and investigating the interplay of topological and symmetry-breaking phases. We use an unsupervised and interpretable machine-learning method, the tensorial-kernel support vector machine, to study the honeycomb Kitaev-$Γ$ model in a magnetic field. Our machine learns the global classical phase diagram and the associated analytical order parameters, including several distinct spin liquids, two exotic $S_3$ magnets, and two modulated $S_3 \times Z_3$ magnets. We find that the extension of Kitaev spin liquids and a field-induced suppression of magnetic order already occur in the large-$S$ limit, implying that critical parts of the physics of Kitaev materials can be understood at the classical level. Moreover, the two $S_3 \times Z_3$ orders are induced by competition between Kitaev and $Γ$ spin liquids and feature a different type of spin-lattice entangled modulation, which requires a matrix description instead of scalar phase factors. Our work provides a direct instance of a machine detecting new phases and paves the way towards the development of automated tools to explore unsolved problems in many-body physics.

cond-mat.str-el↗

arXiv2021

Treewidth of the $q$-Kneser graphs

Let $V$ be an $n$-dimensional vector space over a finite field $\mathbb{F}_q$, where $q$ is a prime power. Define the \emph{generalized $q$-Kneser graph} $K_q(n,k,t)$ to be the graph whose vertices are the $k$-dimensional subspaces of $V$ and two vertices $F_1$ and $F_2$ are adjacent if $\dim(F_1\cap F_2)<t$. Then $K_q(n,k,1)$ is the well-known $q$-Kneser graph. In this paper, we determine the treewidth of $K_q(n,k,t)$ for $n\geq 2t(k-t+1)+k+1$ and $t\ge 1$ exactly. Note that $K_q(n,k,k-1)$ is the complement of the Grassmann graph $G_q(n,k)$. We give a more precise result for the treewidth of $\overline{G_q(n,k)}$ for any possible $n$, $k$ and $q$.

math.CO↗