arXiv subjects

Xin Liu

Publications and source records attributed to Xin Liu.

At least 793 records · Page 44Linked to original sources

arXiv2021

Sampling methods for efficient training of graph convolutional networks: A survey

Graph Convolutional Networks (GCNs) have received significant attention from various research fields due to the excellent performance in learning graph representations. Although GCN performs well compared with other methods, it still faces challenges. Training a GCN model for large-scale graphs in a conventional way requires high computation and storage costs. Therefore, motivated by an urgent need in terms of efficiency and scalability in training GCN, sampling methods have been proposed and achieved a significant effect. In this paper, we categorize sampling methods based on the sampling mechanisms and provide a comprehensive survey of sampling methods for efficient training of GCN. To highlight the characteristics and differences of sampling methods, we present a detailed comparison within each category and further give an overall comparative analysis for the sampling methods in all categories. Finally, we discuss some challenges and future research directions of the sampling methods.

cs.LG↗

arXiv2021

Very Large Array imaging rules out precessing radio jets in three DES$-$SDSS-selected candidate periodic quasars

Periodic quasars have been suggested as candidates for hosting binary supermassive black holes (SMBHs), although alternative scenarios remain possible to explain the optical light curve periodicity. To test the alternative hypothesis of precessing radio jet, we present deep 6 GHz radio imaging conducted with NSF's Karl G. Jansky Very Large Array (VLA) in its C configuration for the three candidate periodic quasars, DES J024703.24$-$010032.0, DES J024944.66$-$000036.8, and DES J025214.67$-$002813.7. Our targets were selected based on their optical variability using 20-yr long multi-color light curves from the Dark Energy Survey (DES) and the Sloan Digital Sky Survey (SDSS). The new VLA observations show that all three periodic quasars are radio-quiet with the radio loudness parameters measured to be $R\equiv f_{6\,{\rm cm}}/f_{\rm 2500}$ of $\lesssim$1.0$-$1.5 and the $k$-corrected luminosities $νL_ν$[6 GHz] of $\lesssim$5$-$21 $\times$ 10$^{39}$ erg s$^{-1}$. They are in stark contrast to previously known periodic quasars proposed as binary SMBH candidates such as the blazar OJ 287 and PG1302$-$102. Our results rule out optical emission contributed from precessing radio jets as the origin of the optical periodicity in the three DES$-$SDSS-selected candidate periodic quasars. Future continued optical monitoring and complementary multi-wavelength observations are still needed to further test the binary SMBH hypothesis as well as other competing scenarios to explain the optical periodicity.

astro-ph.HE↗

arXiv2021

A characteristic optical variability timescale in astrophysical accretion disks

Accretion disks around supermassive black holes in active galactic nuclei produce continuum radiation at ultraviolet and optical wavelengths. Physical processes in the accretion flow lead to stochastic variability of this emission on a wide range of timescales. We measure the optical continuum variability observed in 67 active galactic nuclei and the characteristic timescale at which the variability power spectrum flattens. We find a correlation between this timescale and the black hole mass, extending over the entire mass range of supermassive black holes. This timescale is consistent with the expected thermal timescale at the ultraviolet-emitting radius in standard accretion disk theory. Accreting white dwarfs lie close to this correlation, suggesting a common process for all accretion disks.

astro-ph.GA↗

arXiv2021

Controllable Majorana vortex states in iron-based superconducting nanowires

There has been experimental evidence for the Majorana zero modes (MZMs) in solid state systems, which are building blocks for potential topological quantum computing. It is important to design devices, in which MZMs are easy to manipulate and possess a broad topological non-trivial parameter space for fusion and braiding. Here, we propose that the Majorana vortex states in iron-based superconducting nanowires fulfill these desirable conditions. This system has a radius-induced topological phase transition, giving a lower limit to the radius of the nanowire. In the topological phase, there is only one pair of MZMs in the nanowire over a wide range of radius, chemical potential, and external magnetic field. The wavefunction of the MZM has a sizable distribution at the side edge of the nanowire. This property enables one to control the interaction of the MZMs in neighboring vortex nanowires, and paves the way for Majorana fusion and braiding.

cond-mat.supr-con↗

arXiv2021

AbdomenCT-1K: Is Abdominal Organ Segmentation A Solved Problem?

With the unprecedented developments in deep learning, automatic segmentation of main abdominal organs seems to be a solved problem as state-of-the-art (SOTA) methods have achieved comparable results with inter-rater variability on many benchmark datasets. However, most of the existing abdominal datasets only contain single-center, single-phase, single-vendor, or single-disease cases, and it is unclear whether the excellent performance can generalize on diverse datasets. This paper presents a large and diverse abdominal CT organ segmentation dataset, termed AbdomenCT-1K, with more than 1000 (1K) CT scans from 12 medical centers, including multi-phase, multi-vendor, and multi-disease cases. Furthermore, we conduct a large-scale study for liver, kidney, spleen, and pancreas segmentation and reveal the unsolved segmentation problems of the SOTA methods, such as the limited generalization ability on distinct medical centers, phases, and unseen diseases. To advance the unsolved problems, we further build four organ segmentation benchmarks for fully supervised, semi-supervised, weakly supervised, and continual learning, which are currently challenging and active research topics. Accordingly, we develop a simple and effective method for each benchmark, which can be used as out-of-the-box methods and strong baselines. We believe the AbdomenCT-1K dataset will promote future in-depth research towards clinical applicable abdominal organ segmentation methods. The datasets, codes, and trained models are publicly available at https://github.com/JunMa11/AbdomenCT-1K.

cs.CV↗

arXiv2021

iMiGUE: An Identity-free Video Dataset for Micro-Gesture Understanding and Emotion Analysis

We introduce a new dataset for the emotional artificial intelligence research: identity-free video dataset for Micro-Gesture Understanding and Emotion analysis (iMiGUE). Different from existing public datasets, iMiGUE focuses on nonverbal body gestures without using any identity information, while the predominant researches of emotion analysis concern sensitive biometric data, like face and speech. Most importantly, iMiGUE focuses on micro-gestures, i.e., unintentional behaviors driven by inner feelings, which are different from ordinary scope of gestures from other gesture datasets which are mostly intentionally performed for illustrative purposes. Furthermore, iMiGUE is designed to evaluate the ability of models to analyze the emotional states by integrating information of recognized micro-gesture, rather than just recognizing prototypes in the sequences separately (or isolatedly). This is because the real need for emotion AI is to understand the emotional states behind gestures in a holistic way. Moreover, to counter for the challenge of imbalanced sample distribution of this dataset, an unsupervised learning method is proposed to capture latent representations from the micro-gesture sequences themselves. We systematically investigate representative methods on this dataset, and comprehensive experimental results reveal several interesting insights from the iMiGUE, e.g., micro-gesture-based analysis can promote emotion understanding. We confirm that the new iMiGUE dataset could advance studies of micro-gesture and emotion AI.

cs.CV↗

arXiv2021

Early Mobility Recognition for Intensive Care Unit Patients Using Accelerometers

With the development of the Internet of Things(IoT) and Artificial Intelligence(AI) technologies, human activity recognition has enabled various applications, such as smart homes and assisted living. In this paper, we target a new healthcare application of human activity recognition, early mobility recognition for Intensive Care Unit(ICU) patients. Early mobility is essential for ICU patients who suffer from long-time immobilization. Our system includes accelerometer-based data collection from ICU patients and an AI model to recognize patients' early mobility. To improve the model accuracy and stability, we identify features that are insensitive to sensor orientations and propose a segment voting process that leverages a majority voting strategy to recognize each segment's activity. Our results show that our system improves model accuracy from 77.78\% to 81.86\% and reduces the model instability (standard deviation) from 16.69\% to 6.92\%, compared to the same AI model without our feature engineering and segment voting process.

cs.LG↗

arXiv2021

Bridging Subword Gaps in Pretrain-Finetune Paradigm for Natural Language Generation

A well-known limitation in pretrain-finetune paradigm lies in its inflexibility caused by the one-size-fits-all vocabulary. This potentially weakens the effect when applying pretrained models into natural language generation (NLG) tasks, especially for the subword distributions between upstream and downstream tasks with significant discrepancy. Towards approaching this problem, we extend the vanilla pretrain-finetune pipeline with an extra embedding transfer step. Specifically, a plug-and-play embedding generator is introduced to produce the representation of any input token, according to pre-trained embeddings of its morphologically similar ones. Thus, embeddings of mismatch tokens in downstream tasks can also be efficiently initialized. We conduct experiments on a variety of NLG tasks under the pretrain-finetune fashion. Experimental results and extensive analyses show that the proposed strategy offers us opportunities to feel free to transfer the vocabulary, leading to more efficient and better performed downstream NLG models.

cs.CL↗

arXiv2021

Ultra High Dimensional Change Point Detection

Structural breaks have been commonly seen in applications. Specifically for detection of change points in time, research gap still remains on the setting in ultra high dimension, where the covariates may bear spurious correlations. In this paper, we propose a two-stage approach to detect change points in ultra high dimension, by firstly proposing the dynamic titled current correlation screening method to reduce the input dimension, and then detecting possible change points in the framework of group variable selection. Not only the spurious correlation between ultra-high dimensional covariates is taken into consideration in variable screening, but non-convex penalties are studied in change point detection in the ultra high dimension. Asymptotic properties are derived to guarantee the asymptotic consistency of the selection procedure, and the numerical investigations show the promising performance of the proposed approach.

stat.ME↗

arXiv2021

Multi-hop Graph Convolutional Network with High-order Chebyshev Approximation for Text Reasoning

Graph convolutional network (GCN) has become popular in various natural language processing (NLP) tasks with its superiority in long-term and non-consecutive word interactions. However, existing single-hop graph reasoning in GCN may miss some important non-consecutive dependencies. In this study, we define the spectral graph convolutional network with the high-order dynamic Chebyshev approximation (HDGCN), which augments the multi-hop graph reasoning by fusing messages aggregated from direct and long-term dependencies into one convolutional layer. To alleviate the over-smoothing in high-order Chebyshev approximation, a multi-vote-based cross-attention (MVCAttn) with linear computation complexity is also proposed. The empirical results on four transductive and inductive NLP tasks and the ablation study verify the efficacy of the proposed model. Our source code is available at https://github.com/MathIsAll/HDGCN-pytorch.

cs.CL↗

arXiv2021

Exploring Discourse Structures for Argument Impact Classification

Discourse relations among arguments reveal logical structures of a debate conversation. However, no prior work has explicitly studied how the sequence of discourse relations influence a claim's impact. This paper empirically shows that the discourse relations between two arguments along the context path are essential factors for identifying the persuasive power of an argument. We further propose DisCOC to inject and fuse the sentence-level structural discourse information with contextualized features derived from large-scale language models. Experimental results and extensive analysis show that the attention and gate mechanisms that explicitly model contexts and texts can indeed help the argument impact classification task defined by Durmus et al. (2019), and discourse structures among the context path of the claim to be classified can further boost the performance.

cs.CL↗

arXiv2021

Improving Graph Neural Networks with Simple Architecture Design

Graph Neural Networks have emerged as a useful tool to learn on the data by applying additional constraints based on the graph structure. These graphs are often created with assumed intrinsic relations between the entities. In recent years, there have been tremendous improvements in the architecture design, pushing the performance up in various prediction tasks. In general, these neural architectures combine layer depth and node feature aggregation steps. This makes it challenging to analyze the importance of features at various hops and the expressiveness of the neural network layers. As different graph datasets show varying levels of homophily and heterophily in features and class label distribution, it becomes essential to understand which features are important for the prediction tasks without any prior information. In this work, we decouple the node feature aggregation step and depth of graph neural network and introduce several key design strategies for graph neural networks. More specifically, we propose to use softmax as a regularizer and "Soft-Selector" of features aggregated from neighbors at different hop distances; and "Hop-Normalization" over GNN layers. Combining these techniques, we present a simple and shallow model, Feature Selection Graph Neural Network (FSGNN), and show empirically that the proposed model outperforms other state of the art GNN models and achieves up to 64% improvements in accuracy on node classification tasks. Moreover, analyzing the learned soft-selection parameters of the model provides a simple way to study the importance of features in the prediction tasks. Finally, we demonstrate with experiments that the model is scalable for large graphs with millions of nodes and billions of edges.

stat.ML↗

arXiv2021

FDDH: Fast Discriminative Discrete Hashing for Large-Scale Cross-Modal Retrieval

Cross-modal hashing, favored for its effectiveness and efficiency, has received wide attention to facilitating efficient retrieval across different modalities. Nevertheless, most existing methods do not sufficiently exploit the discriminative power of semantic information when learning the hash codes, while often involving time-consuming training procedure for handling the large-scale dataset. To tackle these issues, we formulate the learning of similarity-preserving hash codes in terms of orthogonally rotating the semantic data so as to minimize the quantization loss of mapping such data to hamming space, and propose an efficient Fast Discriminative Discrete Hashing (FDDH) approach for large-scale cross-modal retrieval. More specifically, FDDH introduces an orthogonal basis to regress the targeted hash codes of training examples to their corresponding semantic labels, and utilizes "-dragging technique to provide provable large semantic margins. Accordingly, the discriminative power of semantic information can be explicitly captured and maximized. Moreover, an orthogonal transformation scheme is further proposed to map the nonlinear embedding data into the semantic subspace, which can well guarantee the semantic consistency between the data feature and its semantic representation. Consequently, an efficient closed form solution is derived for discriminative hash code learning, which is very computationally efficient. In addition, an effective and stable online learning strategy is presented for optimizing modality-specific projection functions, featuring adaptivity to different training sizes and streaming data. The proposed FDDH approach theoretically approximates the bi-Lipschitz continuity, runs sufficiently fast, and also significantly improves the retrieval performance over the state-of-the-art methods. The source code is released at: https://github.com/starxliu/FDDH.

cs.CV↗

arXiv2021

POND: Pessimistic-Optimistic oNline Dispatching

This paper considers constrained online dispatching with unknown arrival, reward and constraint distributions. We propose a novel online dispatching algorithm, named POND, standing for Pessimistic-Optimistic oNline Dispatching, which achieves $O(\sqrt{T})$ regret and $O(1)$ constraint violation. Both bounds are sharp. Our experiments on synthetic and real datasets show that POND achieves low regret with minimal constraint violations.

cs.LG↗

arXiv2021

A hidden population of high-redshift double quasars unveiled by astrometry

Galaxy mergers occur frequently in the early universe and bring multiple supermassive black holes (SMBHs) into the nucleus, where they may eventually coalesce. Identifying post-merger-scale (i.e., <~a few kpc) dual SMBHs is a critical pathway to understanding their dynamical evolution and successive mergers. While serendipitously discovering kpc-scale dual SMBHs at z<1 is possible, such systems are elusive at z>2, but critical to constraining the progenitors of SMBH mergers. The redshift z~2 also marks the epoch of peak activity of luminous quasars, hence probing this spatial regime at high redshift is of particular significance in understanding the evolution of quasars. However, given stringent resolution requirements, there is currently no confirmed <10 kpc physical SMBH pair at z>2. Here we report two sub-arcsec double quasars at z>2 discovered from a targeted search with a novel astrometric technique, demonstrating a high success rate (~50%) in this systematic approach. These high-redshift double quasars could be the long-sought kpc-scale dual SMBHs, or sub-arcsec gravitationally-lensed quasar images. One of these double quasars (at z=2.95) was spatially resolved with optical spectroscopy, and slightly favors the scenario of a physical quasar pair with a projected separation of 3.5 kpc (0.46"). Follow-up observations of double quasars discovered by this targeted approach will be able to provide the first observational constraints on kpc-scale dual SMBHs at z>2.

astro-ph.GA↗

arXiv2021

Generalized Image Reconstruction over T-Algebra

Principal Component Analysis (PCA) is well known for its capability of dimension reduction and data compression. However, when using PCA for compressing/reconstructing images, images need to be recast to vectors. The vectorization of images makes some correlation constraints of neighboring pixels and spatial information lost. To deal with the drawbacks of the vectorizations adopted by PCA, we used small neighborhoods of each pixel to form compounded pixels and use a tensorial version of PCA, called TPCA (Tensorial Principal Component Analysis), to compress and reconstruct a compounded image of compounded pixels. Our experiments on public data show that TPCA compares favorably with PCA in compressing and reconstructing images. We also show in our experiments that the performance of TPCA increases when the order of compounded pixels increases.

cs.CV↗

arXiv2021

Distractor-Aware Fast Tracking via Dynamic Convolutions and MOT Philosophy

A practical long-term tracker typically contains three key properties, i.e. an efficient model design, an effective global re-detection strategy and a robust distractor awareness mechanism. However, most state-of-the-art long-term trackers (e.g., Pseudo and re-detecting based ones) do not take all three key properties into account and therefore may either be time-consuming or drift to distractors. To address the issues, we propose a two-task tracking frame work (named DMTrack), which utilizes two core components (i.e., one-shot detection and re-identification (re-id) association) to achieve distractor-aware fast tracking via Dynamic convolutions (d-convs) and Multiple object tracking (MOT) philosophy. To achieve precise and fast global detection, we construct a lightweight one-shot detector using a novel dynamic convolutions generation method, which provides a unified and more flexible way for fusing target information into the search field. To distinguish the target from distractors, we resort to the philosophy of MOT to reason distractors explicitly by maintaining all potential similarities' tracklets. Benefited from the strength of high recall detection and explicit object association, our tracker achieves state-of-the-art performance on the LaSOT, OxUvA, TLP, VOT2018LT and VOT2019LT benchmarks and runs in real-time (3x faster than comparisons).

cs.CV↗

arXiv2021

A Survey on Federated Learning and its Applications for Accelerating Industrial Internet of Things

Federated learning (FL) brings collaborative intelligence into industries without centralized training data to accelerate the process of Industry 4.0 on the edge computing level. FL solves the dilemma in which enterprises wish to make the use of data intelligence with security concerns. To accelerate industrial Internet of things with the further leverage of FL, existing achievements on FL are developed from three aspects: 1) define terminologies and elaborate a general framework of FL for accommodating various scenarios; 2) discuss the state-of-the-art of FL on fundamental researches including data partitioning, privacy preservation, model optimization, local model transportation, personalization, motivation mechanism, platform & tools, and benchmark; 3) discuss the impacts of FL from the economic perspective. To attract more attention from industrial academia and practice, a FL-transformed manufacturing paradigm is presented, and future research directions of FL are given and possible immediate applications in Industry 4.0 domain are also proposed.

cs.DC↗