arXiv subjects

Jin Liu

Publications and source records attributed to Jin Liu.

At least 145 records · Page 8Linked to original sources

arXiv2022

A Frequency-aware Software Cache for Large Recommendation System Embeddings

Deep learning recommendation models (DLRMs) have been widely applied in Internet companies. The embedding tables of DLRMs are too large to fit on GPU memory entirely. We propose a GPU-based software cache approaches to dynamically manage the embedding table in the CPU and GPU memory space by leveraging the id's frequency statistics of the target dataset. Our proposed software cache is efficient in training entire DLRMs on GPU in a synchronized update manner. It is also scaled to multiple GPUs in combination with the widely used hybrid parallel training approaches. Evaluating our prototype system shows that we can keep only 1.5% of the embedding parameters in the GPU to obtain a decent end-to-end training speed.

cs.IR↗

arXiv2022

Syntax Controlled Knowledge Graph-to-Text Generation with Order and Semantic Consistency

The knowledge graph (KG) stores a large amount of structural knowledge, while it is not easy for direct human understanding. Knowledge graph-to-text (KG-to-text) generation aims to generate easy-to-understand sentences from the KG, and at the same time, maintains semantic consistency between generated sentences and the KG. Existing KG-to-text generation methods phrase this task as a sequence-to-sequence generation task with linearized KG as input and consider the consistency issue of the generated texts and KG through a simple selection between decoded sentence word and KG node word at each time step. However, the linearized KG order is commonly obtained through a heuristic search without data-driven optimization. In this paper, we optimize the knowledge description order prediction under the order supervision extracted from the caption and further enhance the consistency of the generated sentences and KG through syntactic and semantic regularization. We incorporate the Part-of-Speech (POS) syntactic tags to constrain the positions to copy words from the KG and employ a semantic context scoring function to evaluate the semantic fitness for each word in its local context when decoding each word in the generated sentence. Extensive experiments are conducted on two datasets, WebNLG and DART, and achieve state-of-the-art performances.

cs.AI↗

arXiv2022

CODE-MVP: Learning to Represent Source Code from Multiple Views with Contrastive Pre-Training

Recent years have witnessed increasing interest in code representation learning, which aims to represent the semantics of source code into distributed vectors. Currently, various works have been proposed to represent the complex semantics of source code from different views, including plain text, Abstract Syntax Tree (AST), and several kinds of code graphs (e.g., Control/Data Flow Graph). However, most of them only consider a single view of source code independently, ignoring the correspondences among different views. In this paper, we propose to integrate different views with the natural-language description of source code into a unified framework with Multi-View contrastive Pre-training, and name our model as CODE-MVP. Specifically, we first extract multiple code views using compiler tools, and learn the complementary information among them under a contrastive learning framework. Inspired by the type checking in compilation, we also design a fine-grained type inference objective in the pre-training. Experiments on three downstream tasks over five datasets demonstrate the superiority of CODE-MVP when compared with several state-of-the-art baselines. For example, we achieve 2.4/2.3/1.1 gain in terms of MRR/MAP/Accuracy metrics on natural language code retrieval, code similarity, and code defect detection tasks, respectively.

cs.PL↗

arXiv2022

Identification of Autism spectrum disorder based on a novel feature selection method and Variational Autoencoder

The development of noninvasive brain imaging such as resting-state functional magnetic resonance imaging (rs-fMRI) and its combination with AI algorithm provides a promising solution for the early diagnosis of Autism spectrum disorder (ASD). However, the performance of the current ASD classification based on rs-fMRI still needs to be improved. This paper introduces a classification framework to aid ASD diagnosis based on rs-fMRI. In the framework, we proposed a novel filter feature selection method based on the difference between step distribution curves (DSDC) to select remarkable functional connectivities (FCs) and utilized a multilayer perceptron (MLP) which was pretrained by a simplified Variational Autoencoder (VAE) for classification. We also designed a pipeline consisting of a normalization procedure and a modified hyperbolic tangent (tanh) activation function to replace the original tanh function, further improving the model accuracy. Our model was evaluated by 10 times 10-fold cross-validation and achieved an average accuracy of 78.12%, outperforming the state-of-the-art methods reported on the same dataset. Given the importance of sensitivity and specificity in disease diagnosis, two constraints were designed in our model which can improve the model's sensitivity and specificity by up to 9.32% and 10.21%, respectively. The added constraints allow our model to handle different application scenarios and can be used broadly.

eess.IV↗

arXiv2022

Extending Growth Mixture Model to Assess Heterogeneity in Joint Development with Piecewise Linear Trajectories in the Framework of Individual Measurement Occasions

Researchers continue to be interested in exploring the effects that covariates have on the heterogeneity in trajectories. The inclusion of covariates associated with latent classes allows for a more clear understanding of individual differences and a more meaningful interpretation of latent class membership. Many theoretical and empirical studies have focused on investigating heterogeneity in change patterns of a univariate repeated outcome and examining the effects on baseline covariates that inform the cluster formation. However, developmental processes rarely unfold in isolation; therefore, empirical researchers often desire to examine two or more outcomes over time, hoping to understand their joint development where these outcomes and their change patterns are correlated. This study examines the heterogeneity in parallel nonlinear trajectories and identifies baseline characteristics as predictors of latent classes. Our simulation studies show that the proposed model can tell the clusters of parallel trajectories apart and provide unbiased and accurate point estimates with target coverage probabilities for the parameters of interest in general. We illustrate how to apply the model to investigate the heterogeneity in the joint development of reading and mathematics ability from Grade K to 5. In this real-world example, we also demonstrate how to select covariates that contribute the most to the latent classes and transform candidate covariates from a large set into a more manageable set with retaining the meaningful properties of the original set in the structural equation modeling framework.

stat.ME↗

arXiv2022

Obtaining interpretable parameters from reparameterizing longitudinal models: transformation matrices between growth factors in two parameter spaces

The linear spline growth model (LSGM), which approximates complex patterns using at least two linear segments, is a popular tool for examining nonlinear change patterns. Among such models, the linear-linear piecewise change pattern is the most straightforward one. An earlier study has proved that other than the intercept and slopes, the knot (or change-point), at which two linear segments join together, can be estimated as a growth factor in a reparameterized longitudinal model in the latent growth curve modeling framework. However, the reparameterized coefficients were no longer directly related to the underlying developmental process and therefore lacked meaningful, substantive interpretation, although they were simple functions of the original parameters. This study proposes transformation matrices between parameters in the original and reparameterized models so that the interpretable coefficients directly related to the underlying change pattern can be derived from reparameterized ones. Additionally, the study extends the existing linear-linear piecewise model to allow for individual measurement occasions, and investigates predictors for the individual-differences in change patterns. We present the proposed methods with simulation studies and a real-world data analysis. Our simulation studies demonstrate that the proposed method can generally provide an unbiased and consistent estimation of model parameters of interest and confidence intervals with satisfactory coverage probabilities. An empirical example using longitudinal mathematics achievement scores shows that the model can estimate the growth factor coefficients and path coefficients directly related to the underlying developmental process, thereby providing meaningful interpretation. For easier implementation, we also provide the corresponding code for the proposed models.

stat.ME↗

arXiv2022

Compilable Neural Code Generation with Compiler Feedback

Automatically generating compilable programs with (or without) natural language descriptions has always been a touchstone problem for computational linguistics and automated software engineering. Existing deep-learning approaches model code generation as text generation, either constrained by grammar structures in decoder, or driven by pre-trained language models on large-scale code corpus (e.g., CodeGPT, PLBART, and CodeT5). However, few of them account for compilability of the generated programs. To improve compilability of the generated programs, this paper proposes COMPCODER, a three-stage pipeline utilizing compiler feedback for compilable code generation, including language model fine-tuning, compilability reinforcement, and compilability discrimination. Comprehensive experiments on two code generation tasks demonstrate the effectiveness of our proposed approach, improving the success rate of compilation from 44.18 to 89.18 in code completion on average and from 70.3 to 96.2 in text-to-code generation, respectively, when comparing with the state-of-the-art CodeGPT.

cs.CL↗

arXiv2022

Tailoring solid-state single-photon sources with stimulated emissions

The coherent interaction of electromagnetic fields with solid-state two-level systems can yield deterministic quantum light sources for photonic quantum technologies. To date, the performance of semiconductor single-photon sources based on three-level systems is limited mainly due to a lack of high photon indistinguishability. Here, we tailor the cavity-enhanced spontaneous emission from a ladder-type three-level system in a single epitaxial quantum dot (QD) through stimulated emission. After populating the biexciton (XX) of the QD through two-photon resonant excitation (TPE), we use another laser pulse to selectively depopulate the XX state into an exciton (X) state with a predefined polarization. The stimulated XX-X emission modifies the X decay dynamics and yields improved polarized single-photon source characteristics such as a source brightness of 0.030(2), a single-photon purity of 0.998(1), and an indistinguishability of 0.926(4). Our method can be readily applied to existing QD single-photon sources and expands the capabilities of three-level systems for advanced quantum photonic functionalities.

physics.optics↗

arXiv2022

Two-step growth mixture model to examine heterogeneity in nonlinear trajectories

Empirical researchers are usually interested in investigating the impacts of baseline covariates have when uncovering sample heterogeneity and separating samples into more homogeneous groups. However, a considerable number of studies in the structural equation modeling (SEM) framework usually start with vague hypotheses in terms of heterogeneity and possible reasons. It suggests that (1) the determination and specification of a proper model with covariates is not straightforward, and (2) the exploration process may be computational intensive given that a model in the SEM framework is usually complicated and the pool of candidate covariates is usually huge in the psychological and educational domain where the SEM framework is widely employed. Following Bakk and Kuha (2017), this article presents a two-step growth mixture model (GMM) that examines the relationship between latent classes of nonlinear trajectories and baseline characteristics. Our simulation studies demonstrate that the proposed model is capable of clustering the nonlinear change patterns, and estimating the parameters of interest unbiasedly, precisely, as well as exhibiting appropriate confidence interval coverage. Considering the pool of candidate covariates is usually huge and highly correlated, this study also proposes implementing exploratory factor analysis (EFA) to reduce the dimension of covariate space. We illustrate how to use the hybrid method, the two-step GMM and EFA, to efficiently explore the heterogeneity of nonlinear trajectories of longitudinal mathematics achievement data.

stat.ME↗

arXiv2021

MDistMult: A Multiple Scoring Functions Model for Link Prediction on Antiviral Drugs Knowledge Graph

Knowledge graphs (KGs) on COVID-19 have been constructed to accelerate the research process of COVID-19. However, KGs are always incomplete, especially the new constructed COVID-19 KGs. Link prediction task aims to predict missing entities for (e, r, t) or (h, r, e), where h and t are certain entities, e is an entity that needs to be predicted and r is a relation. This task also has the potential to solve COVID-19 related KGs' incomplete problem. Although various knowledge graph embedding (KGE) approaches have been proposed to the link prediction task, these existing methods suffer from the limitation of using a single scoring function, which fails to capture rich features of COVID-19 KGs. In this work, we propose the MDistMult model that leverages multiple scoring functions to extract more features from existing triples. We employ experiments on the CCKS2020 COVID-19 Antiviral Drugs Knowledge Graph (CADKG). The experimental results demonstrate that our MDistMult achieves state-of-the-art performance in link prediction task on the CADKG dataset

cs.CY↗

arXiv2021

Quantum simulation of a three-mode optomechanical system based on the Fredkin-type interaction

The realization of multimode optomechanical interactions in the single-photon strong-coupling regime is a desired task in cavity optomechanics, but it remains a challenge in realistic physical systems. In this work, we propose a reliable scheme to simulate a three-mode optomechanical system working in the single-photon strong-coupling regime based on the Fredkin-type interaction. This is achieved by utilizing two strong drivings to the two exchangly-coupled modes in the Fredkin-type coupling involving one optical mode and two mechanical-like modes. As an application of this enhanced three-mode nonlinear optomechanical coupling, we show how to generate entangled-cat states of the mechanical-like modes using the conditional displacement mechanism. The quantum coherence effects in the generated states are investigated by calculating two-mode joint Wigner function and quantum entanglement. The influence of the dissipation effect on the state generation is considered in the open-system case.

quant-ph↗

arXiv2021

A Deep Generative Approach to Conditional Sampling

We propose a deep generative approach to sampling from a conditional distribution based on a unified formulation of conditional distribution and generalized nonparametric regression function using the noise-outsourcing lemma. The proposed approach aims at learning a conditional generator so that a random sample from the target conditional distribution can be obtained by the action of the conditional generator on a sample drawn from a reference distribution. The conditional generator is estimated nonparametrically with neural networks by matching appropriate joint distributions using the Kullback-Liebler divergence. An appealing aspect of our method is that it allows either of or both the predictor and the response to be high-dimensional and can handle both continuous and discrete type predictors and responses. We show that the proposed method is consistent in the sense that the conditional generator converges in distribution to the underlying conditional distribution under mild conditions. Our numerical experiments with simulated and benchmark image data validate the proposed method and demonstrate that it outperforms several existing conditional density estimation methods.

math.ST↗

arXiv2021

Iron-rich Fe-O compounds with closest-packed layers at core pressures

Oxygen solubility in solid iron is extremely low, even at high pressures and temperatures. Thus far, no Fe-O compounds between Fe and FeO endmembers have been reported experimentally. We observed chemical reactions of Fe with FeO or Fe$_2$O$_3$ $in\ situ$ x-ray diffraction experiments at 220-260 GPa and 3,000-3,500 K. The refined diffraction patterns are consistent with a series of Fe$_n$O (n $>$ 1) compounds (e.g., Fe$_{25}$O$_{13}$ and Fe$_{28}$O$_{14}$) identified using the adaptive genetic algorithm. Like $ε$-Fe in the hexagonal close-packed (hcp) structure, the structures of Fe$_n$O compounds consist of oxygen-only close-packed monolayers distributed between iron-only layers. $Ab\ initio$ calculations show systematic electronic properties of these compounds that have ramifications for the physical properties of Earth's inner core.

cond-mat.mtrl-sci↗

arXiv2021

Rational Polynomial Camera Model Warping for Deep Learning Based Satellite Multi-View Stereo Matching

Satellite multi-view stereo (MVS) imagery is particularly suited for large-scale Earth surface reconstruction. Differing from the perspective camera model (pin-hole model) that is commonly used for close-range and aerial cameras, the cubic rational polynomial camera (RPC) model is the mainstream model for push-broom linear-array satellite cameras. However, the homography warping used in the prevailing learning based MVS methods is only applicable to pin-hole cameras. In order to apply the SOTA learning based MVS technology to the satellite MVS task for large-scale Earth surface reconstruction, RPC warping should be considered. In this work, we propose, for the first time, a rigorous RPC warping module. The rational polynomial coefficients are recorded as a tensor, and the RPC warping is formulated as a series of tensor transformations. Based on the RPC warping, we propose the deep learning based satellite MVS (SatMVS) framework for large-scale and wide depth range Earth surface reconstruction. We also introduce a large-scale satellite image dataset consisting of 519 5120${\times}$5120 images, which we call the TLC SatMVS dataset. The satellite images were acquired from a three-line camera (TLC) that catches triple-view images simultaneously, forming a valuable supplement to the existing open-source WorldView-3 datasets with single-scanline images. Experiments show that the proposed RPC warping module and the SatMVS framework can achieve a superior reconstruction accuracy compared to the pin-hole fitting method and conventional MVS methods. Code and data are available at https://github.com/WHU-GPCV/SatMVS.

eess.IV↗

arXiv2021

SynCoBERT: Syntax-Guided Multi-Modal Contrastive Pre-Training for Code Representation

Code representation learning, which aims to encode the semantics of source code into distributed vectors, plays an important role in recent deep-learning-based models for code intelligence. Recently, many pre-trained language models for source code (e.g., CuBERT and CodeBERT) have been proposed to model the context of code and serve as a basis for downstream code intelligence tasks such as code search, code clone detection, and program translation. Current approaches typically consider the source code as a plain sequence of tokens, or inject the structure information (e.g., AST and data-flow) into the sequential model pre-training. To further explore the properties of programming languages, this paper proposes SynCoBERT, a syntax-guided multi-modal contrastive pre-training approach for better code representations. Specially, we design two novel pre-training objectives originating from the symbolic and syntactic properties of source code, i.e., Identifier Prediction (IP) and AST Edge Prediction (TEP), which are designed to predict identifiers, and edges between two nodes of AST, respectively. Meanwhile, to exploit the complementary information in semantically equivalent modalities (i.e., code, comment, AST) of the code, we propose a multi-modal contrastive learning strategy to maximize the mutual information among different modalities. Extensive experiments on four downstream tasks related to code intelligence show that SynCoBERT advances the state-of-the-art with the same pre-training corpus and model size.

cs.CL↗

arXiv2021

Schr{ö}dinger-F{ö}llmer Sampler: Sampling without Ergodicity

Sampling from probability distributions is an important problem in statistics and machine learning, specially in Bayesian inference when integration with respect to posterior distribution is intractable and sampling from the posterior is the only viable option for inference. In this paper, we propose Schrödinger-Föllmer sampler (SFS), a novel approach for sampling from possibly unnormalized distributions. The proposed SFS is based on the Schrödinger-Föllmer diffusion process on the unit interval with a time dependent drift term, which transports the degenerate distribution at time zero to the target distribution at time one. Comparing with the existing Markov chain Monte Carlo samplers that require ergodicity, no such requirement is needed for SFS. Computationally, SFS can be easily implemented using the Euler-Maruyama discretization. In theoretical analysis, we establish non-asymptotic error bounds for the sampling distribution of SFS in the Wasserstein distance under suitable conditions. We conduct numerical experiments to evaluate the performance of SFS and demonstrate that it is able to generate samples with better quality than several existing methods.

stat.CO↗

arXiv2021

Estimating Knots and Their Association in Parallel Bilinear Spline Growth Curve Models in the Framework of Individual Measurement Occasions

Latent growth curve models with spline functions are flexible and accessible statistical tools for investigating nonlinear change patterns that exhibit distinct phases of development in manifested variables. Among such models, the bilinear spline growth model (BLSGM) is the most straightforward and intuitive but useful. An existing study has demonstrated that the BLSGM allows the knot (or change-point), at which two linear segments join together, to be an additional growth factor other than the intercept and slopes so that researchers can estimate the knot and its variability in the framework of individual measurement occasions. However, developmental processes usually unfold in a joint development where two or more outcomes and their change patterns are correlated over time. As an extension of the existing BLSGM with an unknown knot, this study considers a parallel BLSGM (PBLSGM) for investigating multiple nonlinear growth processes and estimating the knot with its variability of each process as well as the knot-knot association in the framework of individual measurement occasions. We present the proposed model by simulation studies and a real-world data analysis. Our simulation studies demonstrate that the proposed PBLSGM generally estimate the parameters of interest unbiasedly, precisely and exhibit appropriate confidence interval coverage. An empirical example using longitudinal reading scores, mathematics scores, and science scores shows that the model can estimate the knot with its variance for each growth curve and the covariance between two knots. We also provide the corresponding code for the proposed model.

stat.ME↗

arXiv2021

Extending Mixture of Experts Model to Investigate Heterogeneity of Trajectories: When, Where and How to Add Which Covariates

Researchers are usually interested in examining the impact of covariates when separating heterogeneous samples into latent classes that are more homogeneous. The majority of theoretical and empirical studies with such aims have focused on identifying covariates as predictors of class membership in the structural equation modeling framework. In other words, the covariates only indirectly affect the sample heterogeneity. However, the covariates' influence on between-individual differences can also be direct. This article presents a mixture model that investigates covariates to explain within-cluster and between-cluster heterogeneity simultaneously, known as a mixture-of-experts (MoE) model. This study aims to extend the MoE framework to investigate heterogeneity in nonlinear trajectories: to identify latent classes, covariates as predictors to clusters, and covariates that explain within-cluster differences in change patterns over time. Our simulation studies demonstrate that the proposed model generally estimates the parameters unbiasedly, precisely and exhibits appropriate empirical coverage for a nominal 95% confidence interval. This study also proposes implementing structural equation model forests to shrink the covariate space of the proposed mixture model. We illustrate how to select covariates and construct the proposed model with longitudinal mathematics achievement data. Additionally, we demonstrate that the proposed mixture model can be further extended in the structural equation modeling framework by allowing the covariates that have direct effects to be time-varying.

stat.ME↗