Models, code, and papers for "Jie Yang":

Mesh Variational Autoencoders with Edge Contraction Pooling

Aug 07, 2019
Yu-Jie Yuan, Yu-Kun Lai, Jie Yang, Hongbo Fu, Lin Gao

3D shape analysis is an important research topic in computer vision and graphics. While existing methods have generalized image-based deep learning to meshes using graph-based convolutions, the lack of an effective pooling operation restricts the learning capability of their networks. In this paper, we propose a novel pooling operation for mesh datasets with the same connectivity but different geometry, by building a mesh hierarchy using mesh simplification. For this purpose, we develop a modified mesh simplification method to avoid generating highly irregularly sized triangles. Our pooling operation effectively encodes the correspondence between coarser and finer meshes in the hierarchy. We then present a variational auto-encoder structure with the edge contraction pooling and graph-based convolutions, to explore probability latent spaces of 3D surfaces. Our network requires far fewer parameters than the original mesh VAE and thus can handle denser models thanks to our new pooling operation and convolutional kernels. Our evaluation also shows that our method has better generalization ability and is more reliable in various applications, including shape generation, shape interpolation and shape embedding.

  Click for Model/Code and Paper
SDM-NET: Deep Generative Network for Structured Deformable Mesh

Sep 03, 2019
Lin Gao, Jie Yang, Tong Wu, Yu-Jie Yuan, Hongbo Fu, Yu-Kun Lai, Hao Zhang

We introduce SDM-NET, a deep generative neural network which produces structured deformable meshes. Specifically, the network is trained to generate a spatial arrangement of closed, deformable mesh parts, which respect the global part structure of a shape collection, e.g., chairs, airplanes, etc. Our key observation is that while the overall structure of a 3D shape can be complex, the shape can usually be decomposed into a set of parts, each homeomorphic to a box, and the finer-scale geometry of the part can be recovered by deforming the box. The architecture of SDM-NET is that of a two-level variational autoencoder (VAE). At the part level, a PartVAE learns a deformable model of part geometries. At the structural level, we train a Structured Parts VAE (SP-VAE), which jointly learns the part structure of a shape collection and the part geometries, ensuring a coherence between global shape structure and surface details. Through extensive experiments and comparisons with the state-of-the-art deep generative models of shapes, we demonstrate the superiority of SDM-NET in generating meshes with visual quality, flexible topology, and meaningful structures, which benefit shape interpolation and other subsequently modeling tasks.

* Conditionally Accepted to Siggraph Asia 2019 

  Click for Model/Code and Paper
Asymmetric Correlation Quantization Hashing for Cross-modal Retrieval

Jan 14, 2020
Lu Wang, Jie Yang

Due to the superiority in similarity computation and database storage for large-scale multiple modalities data, cross-modal hashing methods have attracted extensive attention in similarity retrieval across the heterogeneous modalities. However, there are still some limitations to be further taken into account: (1) most current CMH methods transform real-valued data points into discrete compact binary codes under the binary constraints, limiting the capability of representation for original data on account of abundant loss of information and producing suboptimal hash codes; (2) the discrete binary constraint learning model is hard to solve, where the retrieval performance may greatly reduce by relaxing the binary constraints for large quantization error; (3) handling the learning problem of CMH in a symmetric framework, leading to difficult and complex optimization objective. To address above challenges, in this paper, a novel Asymmetric Correlation Quantization Hashing (ACQH) method is proposed. Specifically, ACQH learns the projection matrixs of heterogeneous modalities data points for transforming query into a low-dimensional real-valued vector in latent semantic space and constructs the stacked compositional quantization embedding in a coarse-to-fine manner for indicating database points by a series of learnt real-valued codeword in the codebook with the help of pointwise label information regression simultaneously. Besides, the unified hash codes across modalities can be directly obtained by the discrete iterative optimization framework devised in the paper. Comprehensive experiments on diverse three benchmark datasets have shown the effectiveness and rationality of ACQH.

* 12 pages 

  Click for Model/Code and Paper
Cluster-wise Unsupervised Hashing for Cross-Modal Similarity Search

Nov 11, 2019
Lu Wang, Jie Yang

In this paper, we present a new cluster-wise unsupervised hashing (CUH) approach to learn compact binary codes for cross-modal similarity retrieval. We develop a discrete optimization method to jointly learn binary codes and the corresponding hash functions for each modality which can improve the performance, unlike existing cross-modal hashing methods that often drop the binary constraints to obtain the binary codes. Moreover, considering the semantic consistency between observed modalities, our CUH generates one unified hash code for all observed modalities of any instance. Specifically, we construct a co-training framework for learning to hash, in which we simultaneously realize the multi-view clustering and the learning of hash. Firstly, our CUH utilize the re-weighted discriminatively embedded K-means for multi-view clustering to learn the corresponding dimension reduced data and the cluster centroid points in the low-dimensional common subspaces, which are used as the approximation to the corresponding hash codes of original data and the cluster-wise code-prototypes respectively. Secondly, in the process for learning of hash, these cluster-wise code-prototypes can guide the learning of the codes to further improve the performance of the binary codes. The reasonableness and effectiveness of CUH is well demonstrated by comprehensive experiments on diverse benchmark datasets.

* 11 pages, 25 figures 

  Click for Model/Code and Paper
A Review of Semi Supervised Learning Theories and Recent Advances

May 28, 2019
Enmei Tu, Jie Yang

Semi-supervised learning, which has emerged from the beginning of this century, is a new type of learning method between traditional supervised learning and unsupervised learning. The main idea of semi-supervised learning is to introduce unlabeled samples into the model training process to avoid performance (or model) degeneration due to insufficiency of labeled samples. Semi-supervised learning has been applied successfully in many fields. This paper reviews the development process and main theories of semi-supervised learning, as well as its recent advances and importance in solving real-world problems demonstrated by typical application examples.

* Chinese language, 14 pages 

  Click for Model/Code and Paper
Chinese NER Using Lattice LSTM

Jul 05, 2018
Yue Zhang, Jie Yang

We investigate a lattice-structured LSTM model for Chinese NER, which encodes a sequence of input characters as well as all potential words that match a lexicon. Compared with character-based methods, our model explicitly leverages word and word sequence information. Compared with word-based methods, lattice LSTM does not suffer from segmentation errors. Gated recurrent cells allow our model to choose the most relevant characters and words from a sentence for better NER results. Experiments on various datasets show that lattice LSTM outperforms both word-based and character-based LSTM baselines, achieving the best results.

* Accepted at ACL 2018 as Long paper 

  Click for Model/Code and Paper
NCRF++: An Open-source Neural Sequence Labeling Toolkit

Jun 17, 2018
Jie Yang, Yue Zhang

This paper describes NCRF++, a toolkit for neural sequence labeling. NCRF++ is designed for quick implementation of different neural sequence labeling models with a CRF inference layer. It provides users with an inference for building the custom model structure through configuration file with flexible neural feature design and utilization. Built on PyTorch, the core operations are calculated in batch, making the toolkit efficient with the acceleration of GPU. It also includes the implementations of most state-of-the-art neural sequence labeling models such as LSTM-CRF, facilitating reproducing and refinement on those methods.

* ACL 2018, demonstration paper 

  Click for Model/Code and Paper
Bayesian active learning for choice models with deep Gaussian processes

May 04, 2018
Jie Yang, Diego Klabjan

In this paper, we propose an active learning algorithm and models which can gradually learn individual's preference through pairwise comparisons. The active learning scheme aims at finding individual's most preferred choice with minimized number of pairwise comparisons. The pairwise comparisons are encoded into probabilistic models based on assumptions of choice models and deep Gaussian processes. The next-to-compare decision is determined by a novel acquisition function. We benchmark the proposed algorithm and models using functions with multiple local optima and one public airline itinerary dataset. The experiments indicate the effectiveness of our active learning algorithm and models.

  Click for Model/Code and Paper
Estimating Time-Varying Graphical Models

Apr 11, 2018
Jilei Yang, Jie Peng

In this paper, we study time-varying graphical models based on data measured over a temporal grid. Such models are motivated by the needs to describe and understand evolving interacting relationships among a set of random variables in many real applications, for instance the study of how stocks interact with each other and how such interactions change over time. We propose a new model, LOcal Group Graphical Lasso Estimation (loggle), under the assumption that the graph topology changes gradually over time. Specifically, loggle uses a novel local group-lasso type penalty to efficiently incorporate information from neighboring time points and to impose structural smoothness of the graphs. We implement an ADMM based algorithm to fit the loggle model. This algorithm utilizes blockwise fast computation and pseudo-likelihood approximation to improve computational efficiency. An R package loggle has also been developed. We evaluate the performance of loggle by simulation experiments. We also apply loggle to S&P 500 stock price data and demonstrate that loggle is able to reveal the interacting relationships among stocks and among industrial sectors in a time period that covers the recent global financial crisis.

  Click for Model/Code and Paper
Notes on Low-rank Matrix Factorization

May 06, 2016
Yuan Lu, Jie Yang

Low-rank matrix factorization (MF) is an important technique in data science. The key idea of MF is that there exists latent structures in the data, by uncovering which we could obtain a compressed representation of the data. By factorizing an original matrix to low-rank matrices, MF provides a unified method for dimension reduction, clustering, and matrix completion. In this article we review several important variants of MF, including: Basic MF, Non-negative MF, Orthogonal non-negative MF. As can be told from their names, non-negative MF and orthogonal non-negative MF are variants of basic MF with non-negativity and/or orthogonality constraints. Such constraints are useful in specific senarios. In the first part of this article, we introduce, for each of these models, the application scenarios, the distinctive properties, and the optimizing method. By properly adapting MF, we can go beyond the problem of clustering and matrix completion. In the second part of this article, we will extend MF to sparse matrix compeletion, enhance matrix compeletion using various regularization methods, and make use of MF for (semi-)supervised learning by introducing latent space reinforcement and transformation. We will see that MF is not only a useful model but also as a flexible framework that is applicable for various prediction problems.

  Click for Model/Code and Paper
Concept based Attention

May 11, 2016
Jie You, Xin Yang, Matthias Hub

Attention endows animals an ability to concentrate on the most relevant information among a deluge of distractors at any given time, either through volitionally 'top-down' biasing, or driven by automatically 'bottom-up' saliency of stimuli, in favour of advantageous competition in neural modulations for information processing. Nevertheless, instead of being limited to perceive simple features, human and other advanced animals adaptively learn the world into categories and abstract concepts from experiences, imparting the world meanings. This thesis suggests that the high-level cognitive ability of human is more likely driven by attention basing on abstract perceptions, which is defined as concept based attention (CbA).

* NeuroSci.Proc.Suppl. 89 (2007) 4-11 
* 7 pages, 2 figures 

  Click for Model/Code and Paper
Learning to Incorporate Structure Knowledge for Image Inpainting

Feb 12, 2020
Jie Yang, Zhiquan Qi, Yong Shi

This paper develops a multi-task learning framework that attempts to incorporate the image structure knowledge to assist image inpainting, which is not well explored in previous works. The primary idea is to train a shared generator to simultaneously complete the corrupted image and corresponding structures --- edge and gradient, thus implicitly encouraging the generator to exploit relevant structure knowledge while inpainting. In the meantime, we also introduce a structure embedding scheme to explicitly embed the learned structure features into the inpainting process, thus to provide possible preconditions for image completion. Specifically, a novel pyramid structure loss is proposed to supervise structure learning and embedding. Moreover, an attention mechanism is developed to further exploit the recurrent structures and patterns in the image to refine the generated structures and contents. Through multi-task learning, structure embedding besides with attention, our framework takes advantage of the structure knowledge and outperforms several state-of-the-art methods on benchmark datasets quantitatively and qualitatively.

* Accepted by AAAI 2020 

  Click for Model/Code and Paper
A Binary Regression Adaptive Goodness-of-fit Test (BAGofT)

Nov 08, 2019
Jiawei Zhang, Jie Ding, Yuhong Yang

The Pearson's $\chi^2$ test and residual deviance test are two classical goodness-of-fit tests for binary regression models such as logistic regression. These two tests cannot be applied when we have one or more continuous covariates in the data, a quite common situation in practice. In that case, the most widely used approach is the Hosmer-Lemeshow test, which partitions the covariate space into groups according to quantiles of the fitted probabilities from all the observations. However, its grouping scheme is not flexible enough to explore how to adversarially partition the data space in order to enhance the power. In this work, we propose a new methodology, named binary regression adaptive grouping goodness-of-fit test (BAGofT), to address the above concern. It is a two-stage solution where the first stage adaptively selects candidate partitions using "training" data, and the second stage performs $\chi^2$ tests with necessary corrections based on "test" data. A proper data splitting ensures that the test has desirable size and power properties. From our experimental results, BAGofT performs much better than Hosmer-Lemeshow test in many situations.

  Click for Model/Code and Paper
Subword Encoding in Lattice LSTM for Chinese Word Segmentation

Oct 30, 2018
Jie Yang, Yue Zhang, Shuailong Liang

We investigate a lattice LSTM network for Chinese word segmentation (CWS) to utilize words or subwords. It integrates the character sequence features with all subsequences information matched from a lexicon. The matched subsequences serve as information shortcut tunnels which link their start and end characters directly. Gated units are used to control the contribution of multiple input links. Through formula derivation and comparison, we show that the lattice LSTM is an extension of the standard LSTM with the ability to take multiple inputs. Previous lattice LSTM model takes word embeddings as the lexicon input, we prove that subword encoding can give the comparable performance and has the benefit of not relying on any external segmentor. The contribution of lattice LSTM comes from both lexicon and pretrained embeddings information, we find that the lexicon information contributes more than the pretrained embeddings information through controlled experiments. Our experiments show that the lattice structure with subword encoding gives competitive or better results with previous state-of-the-art methods on four segmentation benchmarks. Detailed analyses are conducted to compare the performance of word encoding and subword encoding in lattice LSTM. We also investigate the performance of lattice LSTM structure under different circumstances and when this model works or fails.

* 8 pages 

  Click for Model/Code and Paper
Model Selection Techniques -- An Overview

Oct 22, 2018
Jie Ding, Vahid Tarokh, Yuhong Yang

In the era of big data, analysts usually explore various statistical models or machine learning methods for observed data in order to facilitate scientific discoveries or gain predictive power. Whatever data and fitting procedures are employed, a crucial step is to select the most appropriate model or method from a set of candidates. Model selection is a key ingredient in data analysis for reliable and reproducible statistical inference or prediction, and thus central to scientific studies in fields such as ecology, economics, engineering, finance, political science, biology, and epidemiology. There has been a long history of model selection techniques that arise from researches in statistics, information theory, and signal processing. A considerable number of methods have been proposed, following different philosophies and exhibiting varying performances. The purpose of this article is to bring a comprehensive overview of them, in terms of their motivation, large sample performance, and applicability. We provide integrated and practically relevant discussions on theoretical properties of state-of- the-art model selection approaches. We also share our thoughts on some controversial views on the practice of model selection.


  Click for Model/Code and Paper
Design Challenges and Misconceptions in Neural Sequence Labeling

Jul 12, 2018
Jie Yang, Shuailong Liang, Yue Zhang

We investigate the design challenges of constructing effective and efficient neural sequence labeling systems, by reproducing twelve neural sequence labeling models, which include most of the state-of-the-art structures, and conduct a systematic model comparison on three benchmarks (i.e. NER, Chunking, and POS tagging). Misconceptions and inconsistent conclusions in existing literature are examined and clarified under statistical experiments. In the comparison and analysis process, we reach several practical conclusions which can be useful to practitioners.

* Accepted by COLING 2018 (Best Paper Award) 

  Click for Model/Code and Paper
Robustness of classification ability of spiking neural networks

Jan 30, 2018
Jie Yang, Pingping Zhang, Yan Liu

It is well-known that the robustness of artificial neural networks (ANNs) is important for their wide ranges of applications. In this paper, we focus on the robustness of the classification ability of a spiking neural network which receives perturbed inputs. Actually, the perturbation is allowed to be arbitrary styles. However, Gaussian perturbation and other regular ones have been rarely investigated. For classification problems, the closer to the desired point, the more perturbed points there are in the input space. In addition, the perturbation may be periodic. Based on these facts, we only consider sinusoidal and Gaussian perturbations in this paper. With the SpikeProp algorithm, we perform extensive experiments on the classical XOR problem and other three benchmark datasets. The numerical results show that there is not significant reduction in the classification ability of the network if the input signals are subject to sinusoidal and Gaussian perturbations.

* Aceppted by Nonlinear Dynamics 

  Click for Model/Code and Paper
Neural Reranking for Named Entity Recognition

Jul 17, 2017
Jie Yang, Yue Zhang, Fei Dong

We propose a neural reranking system for named entity recognition (NER). The basic idea is to leverage recurrent neural network models to learn sentence-level patterns that involve named entity mentions. In particular, given an output sentence produced by a baseline NER model, we replace all entity mentions, such as \textit{Barack Obama}, into their entity types, such as \textit{PER}. The resulting sentence patterns contain direct output information, yet is less sparse without specific named entities. For example, "PER was born in LOC" can be such a pattern. LSTM and CNN structures are utilised for learning deep representations of such sentences for reranking. Results show that our system can significantly improve the NER accuracies over two different baselines, giving the best reported results on a standard benchmark.

* Accepted as regular paper by RANLP 2017 

  Click for Model/Code and Paper
Indefinite Kernel Logistic Regression

Jul 06, 2017
Fanghui Liu, Xiaolin Huang, Jie Yang

Traditionally, kernel learning methods requires positive definitiveness on the kernel, which is too strict and excludes many sophisticated similarities, that are indefinite, in multimedia area. To utilize those indefinite kernels, indefinite learning methods are of great interests. This paper aims at the extension of the logistic regression from positive semi-definite kernels to indefinite kernels. The model, called indefinite kernel logistic regression (IKLR), keeps consistency to the regular KLR in formulation but it essentially becomes non-convex. Thanks to the positive decomposition of an indefinite matrix, IKLR can be transformed into a difference of two convex models, which follows the use of concave-convex procedure. Moreover, we employ an inexact solving scheme to speed up the sub-problem and develop a concave-inexact-convex procedure (CCICP) algorithm with theoretical convergence analysis. Systematical experiments on multi-modal datasets demonstrate the superiority of the proposed IKLR method over kernel logistic regression with positive definite kernels and other state-of-the-art indefinite learning based algorithms.

* Note that this is not the camera-ready version 

  Click for Model/Code and Paper