arXiv subjects

Haitao Lin

Publications and source records attributed to Haitao Lin.

81 records · Page 5Linked to original sources

arXiv2021

Augmenting Slot Values and Contexts for Spoken Language Understanding with Pretrained Models

Spoken Language Understanding (SLU) is one essential step in building a dialogue system. Due to the expensive cost of obtaining the labeled data, SLU suffers from the data scarcity problem. Therefore, in this paper, we focus on data augmentation for slot filling task in SLU. To achieve that, we aim at generating more diverse data based on existing data. Specifically, we try to exploit the latent language knowledge from pretrained language models by finetuning them. We propose two strategies for finetuning process: value-based and context-based augmentation. Experimental results on two public SLU datasets have shown that compared with existing data augmentation methods, our proposed method can generate more diverse sentences and significantly improve the performance on SLU.

cs.CL↗

arXiv2021

Invertible Manifold Learning for Dimension Reduction

Dimension reduction (DR) aims to learn low-dimensional representations of high-dimensional data with the preservation of essential information. In the context of manifold learning, we define that the representation after information-lossless DR preserves the topological and geometric properties of data manifolds formally, and propose a novel two-stage DR method, called invertible manifold learning (inv-ML) to bridge the gap between theoretical information-lossless and practical DR. The first stage includes a homeomorphic sparse coordinate transformation to learn low-dimensional representations without destroying topology and a local isometry constraint to preserve local geometry. In the second stage, a linear compression is implemented for the trade-off between the target dimension and the incurred information loss in excessive DR scenarios. Experiments are conducted on seven datasets with a neural network implementation of inv-ML, called i-ML-Enc. Empirically, i-ML-Enc achieves invertible DR in comparison with typical existing methods as well as reveals the characteristics of the learned manifolds. Through latent space interpolation on real-world datasets, we find that the reliability of tangent space approximated by the local neighborhood is the key to the success of manifold-based DR algorithms.

cs.LG↗

arXiv2021

GraphMixup: Improving Class-Imbalanced Node Classification on Graphs by Self-supervised Context Prediction

Recent years have witnessed great success in handling node classification tasks with Graph Neural Networks (GNNs). However, most existing GNNs are based on the assumption that node samples for different classes are balanced, while for many real-world graphs, there exists the problem of class imbalance, i.e., some classes may have much fewer samples than others. In this case, directly training a GNN classifier with raw data would under-represent samples from those minority classes and result in sub-optimal performance. This paper presents GraphMixup, a novel mixup-based framework for improving class-imbalanced node classification on graphs. However, directly performing mixup in the input space or embedding space may produce out-of-domain samples due to the extreme sparsity of minority classes; hence we construct semantic relation spaces that allows the Feature Mixup to be performed at the semantic level. Moreover, we apply two context-based self-supervised techniques to capture both local and global information in the graph structure and then propose Edge Mixup specifically for graph data. Finally, we develop a \emph{Reinforcement Mixup} mechanism to adaptively determine how many samples are to be generated by mixup for those minority classes. Extensive experiments on three real-world datasets show that GraphMixup yields truly encouraging results for class-imbalanced node classification tasks.

cs.LG↗

arXiv2020

LookHops: light multi-order convolution and pooling for graph classification

Convolution and pooling are the key operations to learn hierarchical representation for graph classification, where more expressive $k$-order($k>1$) method requires more computation cost, limiting the further applications. In this paper, we investigate the strategy of selecting $k$ via neighborhood information gain and propose light $k$-order convolution and pooling requiring fewer parameters while improving the performance. Comprehensive and fair experiments through six graph classification benchmarks show: 1) the performance improvement is consistent to the $k$-order information gain. 2) the proposed convolution requires fewer parameters while providing competitive results. 3) the proposed pooling outperforms SOTA algorithms in terms of efficiency and performance.

cs.LG↗

arXiv2020

Clustering Based on Graph of Density Topology

Data clustering with uneven distribution in high level noise is challenging. Currently, HDBSCAN is considered as the SOTA algorithm for this problem. In this paper, we propose a novel clustering algorithm based on what we call graph of density topology (GDT). GDT jointly considers the local and global structures of data samples: firstly forming local clusters based on a density growing process with a strategy for properly noise handling as well as cluster boundary detection; and then estimating a GDT from relationship between local clusters in terms of a connectivity measure, givingglobal topological graph. The connectivity, measuring similarity between neighboring local clusters, is based on local clusters rather than individual points, ensuring its robustness to even very large noise. Evaluation results on both toy and real-world datasets show that GDT achieves the SOTA performance by far on almost all the popular datasets, and has a low time complexity of O(nlogn). The code is available at https://github.com/gaozhangyang/DGC.git.

cs.LG↗

arXiv2020

Pulsar Candidate Sifting Using Multi-input Convolution Neural Networks

Pulsar candidate sifting is an essential process for discovering new pulsars. It aims to search for the most promising pulsar candidates from an all-sky survey, such as High Time Resolution Universe (HTRU), Green Bank Northern Celestial Cap (GBNCC), Five-hundred-meter Aperture Spherical radio Telescope (FAST), etc. Recently, machine learning (ML) is a hot topic in pulsar candidate sifting investigations. However, one typical challenge in ML for pulsar candidate sifting comes from the learning difficulty arising from the highly class-imbalance between the observation numbers of pulsars and non-pulsars. Therefore, this work proposes a novel framework for candidate sifting, named multi-input convolutional neural networks (MICNN). The MICNN is an architecture of deep learning with four diagnostic plots of a pulsar candidate as its inputs. To train our MICNN in a highly class-imbalanced dataset, a novel image augment technique, as well as a three-stage training strategy, is proposed. Experiments on observations from HTRU and GBNCC show the effectiveness and robustness of these proposed techniques. In the experiments on HTRU, our MICNN model achieves a recall of 0.962 and a precision rate of 0.967 even in a highly class-imbalanced test dataset.

astro-ph.IM↗

arXiv2020

Neural Pose Transfer by Spatially Adaptive Instance Normalization

Pose transfer has been studied for decades, in which the pose of a source mesh is applied to a target mesh. Particularly in this paper, we are interested in transferring the pose of source human mesh to deform the target human mesh, while the source and target meshes may have different identity information. Traditional studies assume that the paired source and target meshes are existed with the point-wise correspondences of user annotated landmarks/mesh points, which requires heavy labelling efforts. On the other hand, the generalization ability of deep models is limited, when the source and target meshes have different identities. To break this limitation, we proposes the first neural pose transfer model that solves the pose transfer via the latest technique for image style transfer, leveraging the newly proposed component -- spatially adaptive instance normalization. Our model does not require any correspondences between the source and target meshes. Extensive experiments show that the proposed model can effectively transfer deformation from source to target meshes, and has good generalization ability to deal with unseen identities or poses of meshes. Code is available at https://github.com/jiashunwang/Neural-Pose-Transfer .

cs.CV↗

arXiv2020

Concat Convolutional Neural Network for Pulsar Candidate Selection

Pulsar searching is essential for the scientific research in the field of physics and astrophysics. As the development of the radio telescope, the exploding volume and it growth speed of candidates growth have brought about several challenges. Therefore, there is an urgent demand for developing an automatic, accurate and efficient pulsar candidate selection method. To meet this need, this work designed a Concat Convolutional Neural Network (CCNN) to identify the candidates collected from the Five-hundred-meter Aperture Spherical Telescope (FAST) data. The CCNN extracts some "pulsar-like" patterns from the diagnostic subplots using Convolutional Neural Network (CNN) and combines these CNN features by a concatenate layer. Therefore, the CCNN is an end-to-end learning model without any need for any intermediate labels, which makes CCNN suitable for the online learning pipeline of pulsar candidate selection. Experimental results on FAST data show that the CCNN outperforms the available state-of-the-art models in similar scenario. It only misses 4 real pulsars out of 326 totally.

astro-ph.IM↗

arXiv2020

Pulsars Detection by Machine Learning with Very Few Features

It is an active topic to investigate the schemes based on machine learning (ML) methods for detecting pulsars as the data volume growing exponentially in modern surveys. To improve the detection performance, input features into an ML model should be investigated specifically. In the existing pulsar detection researches based on ML methods, there are mainly two kinds of feature designs: the empirical features and statistical features. Due to the combinational effects from multiple features, however, there exist some redundancies and even irrelevant components in the available features, which can reduce the accuracy of a pulsar detection model. Therefore, it is essential to select a subset of relevant features from a set of available candidate features and known as {\itshape feature selection.} In this work, two feature selection algorithms ----\textit{Grid Search} (GS) and \textit{Recursive Feature Elimination} (RFE)---- are proposed to improve the detection performance by removing the redundant and irrelevant features. The algorithms were evaluated on the Southern High Time Resolution University survey (HTRU-S) with five pulsar detection models. The experimental results verify the effectiveness and efficiency of our proposed feature selection algorithms. By the GS, a model with only two features reach a recall rate as high as 99\% and a false positive rate (FPR) as low as 0.65\%; By the RFE, another model with only three features achieves a recall rate 99\% and an FPR of 0.16\% in pulsar candidates classification. Furthermore, this work investigated the number of features required as well as the misclassified pulsars by our models.

astro-ph.IM↗