arXiv subjects

Guoliang Li

Publications and source records attributed to Guoliang Li.

At least 163 records · Page 9Linked to original sources

arXiv2021

Wireless Sensing With Deep Spectrogram Network and Primitive Based Autoregressive Hybrid Channel Model

Human motion recognition (HMR) based on wireless sensing is a low-cost technique for scene understanding. Current HMR systems adopt support vector machines (SVMs) and convolutional neural networks (CNNs) to classify radar signals. However, whether a deeper learning model could improve the system performance is currently not known. On the other hand, training a machine learning model requires a large dataset, but data gathering from experiment is cost-expensive and time-consuming. Although wireless channel models can be adopted for dataset generation, current channel models are mostly designed for communication rather than sensing. To address the above problems, this paper proposes a deep spectrogram network (DSN) by leveraging the residual mapping technique to enhance the HMR performance. Furthermore, a primitive based autoregressive hybrid (PBAH) channel model is developed, which facilitates efficient training and testing dataset generation for HMR in a virtual environment. Experimental results demonstrate that the proposed PBAH channel model matches the actual experimental data very well and the proposed DSN achieves significantly smaller recognition error than that of CNN.

cs.IT↗

arXiv2021

RPT: Relational Pre-trained Transformer Is Almost All You Need towards Democratizing Data Preparation

Can AI help automate human-easy but computer-hard data preparation tasks that burden data scientists, practitioners, and crowd workers? We answer this question by presenting RPT, a denoising auto-encoder for tuple-to-X models (X could be tuple, token, label, JSON, and so on). RPT is pre-trained for a tuple-to-tuple model by corrupting the input tuple and then learning a model to reconstruct the original tuple. It adopts a Transformer-based neural translation architecture that consists of a bidirectional encoder (similar to BERT) and a left-to-right autoregressive decoder (similar to GPT), leading to a generalization of both BERT and GPT. The pre-trained RPT can already support several common data preparation tasks such as data cleaning, auto-completion and schema matching. Better still, RPT can be fine-tuned on a wide range of data preparation tasks, such as value normalization, data transformation, data annotation, etc. To complement RPT, we also discuss several appealing techniques such as collaborative training and few-shot learning for entity resolution, and few-shot learning and NLP question-answering for information extraction. In addition, we identify a series of research opportunities to advance the field of data preparation.

cs.LG↗

arXiv2020

Representation Learning from Limited Educational Data with Crowdsourced Labels

Representation learning has been proven to play an important role in the unprecedented success of machine learning models in numerous tasks, such as machine translation, face recognition and recommendation. The majority of existing representation learning approaches often require a large number of consistent and noise-free labels. However, due to various reasons such as budget constraints and privacy concerns, labels are very limited in many real-world scenarios. Directly applying standard representation learning approaches on small labeled data sets will easily run into over-fitting problems and lead to sub-optimal solutions. Even worse, in some domains such as education, the limited labels are usually annotated by multiple workers with diverse expertise, which yields noises and inconsistency in such crowdsourcing settings. In this paper, we propose a novel framework which aims to learn effective representations from limited data with crowdsourced labels. Specifically, we design a grouping based deep neural network to learn embeddings from a limited number of training samples and present a Bayesian confidence estimator to capture the inconsistency among crowdsourced labels. Furthermore, to expedite the training process, we develop a hard example selection procedure to adaptively pick up training examples that are misclassified by the model. Extensive experiments conducted on three real-world data sets demonstrate the superiority of our framework on learning representations from limited data with crowdsourced labels, comparing with various state-of-the-art baselines. In addition, we provide a comprehensive analysis on each of the main components of our proposed framework and also introduce the promising results it achieved in our real production to fully understand the proposed framework.

cs.LG↗

arXiv2020

Relational Data Synthesis using Generative Adversarial Networks: A Design Space Exploration

The proliferation of big data has brought an urgent demand for privacy-preserving data publishing. Traditional solutions to this demand have limitations on effectively balancing the tradeoff between privacy and utility of the released data. Thus, the database community and machine learning community have recently studied a new problem of relational data synthesis using generative adversarial networks (GAN) and proposed various algorithms. However, these algorithms are not compared under the same framework and thus it is hard for practitioners to understand GAN's benefits and limitations. To bridge the gaps, we conduct so far the most comprehensive experimental study that investigates applying GAN to relational data synthesis. We introduce a unified GAN-based framework and define a space of design solutions for each component in the framework, including neural network architectures and training strategies. We conduct extensive experiments to explore the design space and compare with traditional data synthesis approaches. Through extensive experiments, we find that GAN is very promising for relational data synthesis, and provide guidance for selecting appropriate design solutions. We also point out limitations of GAN and identify future research directions.

cs.DB↗

arXiv2020

Neural Multi-Task Learning for Teacher Question Detection in Online Classrooms

Asking questions is one of the most crucial pedagogical techniques used by teachers in class. It not only offers open-ended discussions between teachers and students to exchange ideas but also provokes deeper student thought and critical analysis. Providing teachers with such pedagogical feedback will remarkably help teachers improve their overall teaching quality over time in classrooms. Therefore, in this work, we build an end-to-end neural framework that automatically detects questions from teachers' audio recordings. Compared with traditional methods, our approach not only avoids cumbersome feature engineering, but also adapts to the task of multi-class question detection in real education scenarios. By incorporating multi-task learning techniques, we are able to strengthen the understanding of semantic relations among different types of questions. We conducted extensive experiments on the question detection tasks in a real-world online classroom dataset and the results demonstrate the superiority of our model in terms of various evaluation metrics.

cs.CL↗

arXiv2020

Temporal Network Representation Learning via Historical Neighborhoods Aggregation

Network embedding is an effective method to learn low-dimensional representations of nodes, which can be applied to various real-life applications such as visualization, node classification, and link prediction. Although significant progress has been made on this problem in recent years, several important challenges remain, such as how to properly capture temporal information in evolving networks. In practice, most networks are continually evolving. Some networks only add new edges or nodes such as authorship networks, while others support removal of nodes or edges such as internet data routing. If patterns exist in the changes of the network structure, we can better understand the relationships between nodes and the evolution of the network, which can be further leveraged to learn node representations with more meaningful information. In this paper, we propose the Embedding via Historical Neighborhoods Aggregation (EHNA) algorithm. More specifically, we first propose a temporal random walk that can identify relevant nodes in historical neighborhoods which have impact on edge formations. Then we apply a deep learning model which uses a custom attention mechanism to induce node embeddings that directly capture temporal information in the underlying feature representation. We perform extensive experiments on a range of real-world datasets, and the results demonstrate the effectiveness of our new approach in the network reconstruction task and the link prediction task.

cs.LG↗

arXiv2019

Towards Interpretable and Learnable Risk Analysis for Entity Resolution

Machine-learning-based entity resolution has been widely studied. However, some entity pairs may be mislabeled by machine learning models and existing studies do not study the risk analysis problem -- predicting and interpreting which entity pairs are mislabeled. In this paper, we propose an interpretable and learnable framework for risk analysis, which aims to rank the labeled pairs based on their risks of being mislabeled. We first describe how to automatically generate interpretable risk features, and then present a learnable risk model and its training technique. Finally, we empirically evaluate the performance of the proposed approach on real data. Our extensive experiments have shown that the learning risk model can identify the mislabeled pairs with considerably higher accuracy than the existing alternatives.

cs.DB↗

arXiv2019

An End-to-End Deep RL Framework for Task Arrangement in Crowdsourcing Platforms

In this paper, we propose a Deep Reinforcement Learning (RL) framework for task arrangement, which is a critical problem for the success of crowdsourcing platforms. Previous works conduct the personalized recommendation of tasks to workers via supervised learning methods. However, the majority of them only consider the benefit of either workers or requesters independently. In addition, they cannot handle the dynamic environment and may produce sub-optimal results. To address these issues, we utilize Deep Q-Network (DQN), an RL-based method combined with a neural network to estimate the expected long-term return of recommending a task. DQN inherently considers the immediate and future reward simultaneously and can be updated in real-time to deal with evolving data and dynamic changes. Furthermore, we design two DQNs that capture the benefit of both workers and requesters and maximize the profit of the platform. To learn value functions in DQN effectively, we also propose novel state representations, carefully design the computation of Q values, and predict transition probabilities and future states. Experiments on synthetic and real datasets demonstrate the superior performance of our framework.

cs.LG↗

arXiv2019

Technical Report: Optimizing Human Involvement for Entity Matching and Consolidation

An end-to-end data integration system requires human feedback in several phases, including collecting training data for entity matching, debugging the resulting clusters, confirming transformations applied on these clusters for data standardization, and finally, reducing each cluster to a single, canonical representation (or "golden record"). The traditional wisdom is to sequentially apply the human feedback, obtained by asking specific questions, within some budget in each phase. However, these questions are highly correlated; the answer to one can influence the outcome of any of the phases of the pipeline. Hence, interleaving them has the potential to offer significant benefits. In this paper, we propose a human-in-the-loop framework that interleaves different types of questions to optimize human involvement. We propose benefit models to measure the quality improvement from asking a question, and cost models to measure the human time it takes to answer a question. We develop a question scheduling framework that judiciously selects questions to maximize the accuracy of the final golden records. Experimental results on three real-world datasets show that our holistic method significantly improves the quality of golden records from 70% to 90%, compared with the state-of-the-art approaches.

cs.DB↗

arXiv2019

An End-to-End Learning-based Cost Estimator

Cost and cardinality estimation is vital to query optimizer, which can guide the plan selection. However traditional empirical cost and cardinality estimation techniques cannot provide high-quality estimation, because they cannot capture the correlation between multiple columns. Recently the database community shows that the learning-based cardinality estimation is better than the empirical methods. However, existing learning-based methods have several limitations. Firstly, they can only estimate the cardinality, but cannot estimate the cost. Secondly, convolutional neural network (CNN) with average pooling is hard to represent complicated structures, e.g., complex predicates, and the model is hard to be generalized. To address these challenges, we propose an effective end-to-end learning-based cost estimation framework based on a tree-structured model, which can estimate both cost and cardinality simultaneously. To the best of our knowledge, this is the first end-to-end cost estimator based on deep learning. We propose effective feature extraction and encoding techniques, which consider both queries and physical operations in feature extraction. We embed these features into our tree-structured model. We propose an effective method to encode string values, which can improve the generalization ability for predicate matching. As it is prohibitively expensive to enumerate all string values, we design a patten-based method, which selects patterns to cover string values and utilizes the patterns to embed string values. We conducted experiments on real-world datasets and experimental results showed that our method outperformed baselines.

cs.DB↗

arXiv2019

VizNet: Towards A Large-Scale Visualization Learning and Benchmarking Repository

Researchers currently rely on ad hoc datasets to train automated visualization tools and evaluate the effectiveness of visualization designs. These exemplars often lack the characteristics of real-world datasets, and their one-off nature makes it difficult to compare different techniques. In this paper, we present VizNet: a large-scale corpus of over 31 million datasets compiled from open data repositories and online visualization galleries. On average, these datasets comprise 17 records over 3 dimensions and across the corpus, we find 51% of the dimensions record categorical data, 44% quantitative, and only 5% temporal. VizNet provides the necessary common baseline for comparing visualization design techniques, and developing benchmark models and algorithms for automating visual analysis. To demonstrate VizNet's utility as a platform for conducting online crowdsourced experiments at scale, we replicate a prior study assessing the influence of user task and data distribution on visual encoding effectiveness, and extend it by considering an additional task: outlier detection. To contend with running such studies at scale, we demonstrate how a metric of perceptual effectiveness can be learned from experimental results, and show its predictive power across test datasets.

cs.HC↗

arXiv2019

Testing Shear Recovery with Field Distortion

The tilt, rotation, or offset of each CCD with respect to the focal plane, as well as the distortion of the focal plane itself, cause shape distortions to the observed objects, an effect typically known as field distortion (FD). We point out that FD provides a unique way of quantifying the accuracy of cosmic shear measurement. The idea is to stack the shear estimators from galaxies that share similar FD-induced shape distortions. Given that the latter can be calculated with parameters from astrometric calibrations, the accuracy of the shear estimator can be directly tested on real images. It provides a way to calibrate the multiplicative and additive shear recovery biases within the scientific data itself, without requiring simulations or any external data sets. We use the CFHTLenS images to demonstrate the accuracy of the Fourier_Quad shear recovery method. We highlight some details in our image processing pipeline, including background removal, source identification and deblending, astrometric calibration, star selection for PSF reconstruction, noise reduction, etc.. We show that in the shear ranges of -0.005 < g_1 < 0.005 and -0.008 < g_2 < 0.008, the multiplicative biases are at the level of < 0.04. Slight additive biases on the order of 5E-4 (6 sigma) are identified for sources provided by the official CFHTLenS catalog (not using its shear catalog), but are minor (4 sigma) for source catalog generated by our Fourier_Quad pipeline.

astro-ph.CO↗

arXiv2018

Crowd-Powered Data Mining

Many data mining tasks cannot be completely addressed by auto- mated processes, such as sentiment analysis and image classification. Crowdsourcing is an effective way to harness the human cognitive ability to process these machine-hard tasks. Thanks to public crowdsourcing platforms, e.g., Amazon Mechanical Turk and Crowd- Flower, we can easily involve hundreds of thousands of ordinary workers (i.e., the crowd) to address these machine-hard tasks. In this tutorial, we will survey and synthesize a wide spectrum of existing studies on crowd-powered data mining. We first give an overview of crowdsourcing, and then summarize the fundamental techniques, including quality control, cost control, and latency control, which must be considered in crowdsourced data mining. Next we review crowd-powered data mining operations, including classification, clustering, pattern mining, machine learning using the crowd (including deep learning, transfer learning and semi-supervised learning) and knowledge discovery. Finally, we provide the emerging challenges in crowdsourced data mining.

cs.DB↗

arXiv2018

Trajectory-driven Influential Billboard Placement

In this paper we propose and study the problem of trajectory-driven influential billboard placement: given a set of billboards $U$ (each with a location and a cost), a database of trajectories $\mathcal{T}$ and a budget $L$, find a set of billboards within the budget to influence the largest number of trajectories. One core challenge is to identify and reduce the overlap of the influence from different billboards to the same trajectories, while keeping the budget constraint into consideration. We show that this problem is NP-hard and present an enumeration based algorithm with $(1-1/e)$ approximation ratio. However, the enumeration should be very costly when $|U|$ is large. By exploiting the locality property of billboards' influence, we propose a partition-based framework PartSel. PartSel partitions $U$ into a set of small clusters, computes the locally influential billboards for each cluster, and merges them to generate the global solution. Since the local solutions can be obtained much more efficient than the global one, PartSel should reduce the computation cost greatly; meanwhile it achieves a non-trivial approximation ratio guarantee. Then we propose a LazyProbe method to further prune billboards with low marginal influence, while achieving the same approximation ratio as PartSel. Experiments on real datasets verify the efficiency and effectiveness of our methods.

cs.SI↗

arXiv2018

Prediction of Supernova Rates in Known Galaxy-galaxy Strong-lens Systems

We propose a new strategy of finding strongly-lensed supernovae (SNe) by monitoring known galaxy-scale strong-lens systems. Strongly lensed SNe are potentially powerful tools for the study of cosmology, galaxy evolution, and stellar populations, but they are extremely rare. By targeting known strongly lensed starforming galaxies, our strategy significantly boosts the detection efficiency for lensed SNe compared to a blind search. As a reference sample, we compile the 128 galaxy-galaxy strong-lens systems from the Sloan Lens ACS Survey (SLACS), the SLACS for the Masses Survey, and the Baryon Oscillation Spectroscopic Survey Emission-Line Lens Survey. Within this sample, we estimate the rates of strongly-lensed Type Ia SN (SNIa) and core-collapse SN (CCSN) to be $1.23 \pm 0.12$ and $10.4 \pm 1.1$ events per year, respectively. The lensed SN images are expected to be widely separated with a median separation of 2 arcsec. Assuming a conservative fiducial lensing magnification factor of 5 for the most highly magnified SN image, we forecast that a monitoring program with a single-visit depth of 24.7 mag (5$σ$ point source, $r$ band) and a cadence of 5 days can detect 0.49 strongly-lensed SNIa event and 2.1 strongly-lensed CCSN events per year within this sample. Our proposed targeted-search strategy is particularly useful for prompt and efficient identifications and follow-up observations of strongly-lensed SN candidates. It also allows telescopes with small field of views and limited time to efficiently discover strongly-lensed SNe with a pencil-beam scanning strategy.

astro-ph.GA↗

arXiv2018

Unsupervised String Transformation Learning for Entity Consolidation

Data integration has been a long-standing challenge in data management with many applications. A key step in data integration is entity consolidation. It takes a collection of clusters of duplicate records as input and produces a single "golden record" for each cluster, which contains the canonical value for each attribute. Truth discovery and data fusion methods, as well as Master Data Management (MDM) systems, can be used for entity consolidation. However, to achieve better results, the variant values (i.e., values that are logically the same with different formats) in the clusters need to be consolidated before applying these methods. For this purpose, we propose a data-driven method to standardize the variant values based on two observations: (1) the variant values usually can be transformed to the same representation (e.g., "Mary Lee" and "Lee, Mary") and (2) the same transformation often appears repeatedly across different clusters (e.g., transpose the first and last name). Our approach first uses an unsupervised method to generate groups of value pairs that can be transformed in the same way (i.e., they share a transformation). Then the groups are presented to a human for verification and the approved ones are used to standardize the data. In a real-world dataset with 17,497 records, our method achieved 75% recall and 99.5% precision in standardizing variant values by asking a human 100 yes/no questions, which completely outperformed a state of the art data wrangling tool.

cs.DB↗

arXiv2018

The Correspondence between Convergence Peaks from Weak Lensing and Massive Dark Matter Haloes

The convergence peaks, constructed from galaxy shape measurement in weak lensing, is a powerful probe of cosmology as the peaks can be connected with the underlined dark matter haloes. However the capability of convergence peak statistic is affected by the noise in galaxy shape measurement, signal to noise ratio as well as the contribution from the projected mass distribution from the large-scale structures along the line of sight (LOS). In this paper we use the ray-tracing simulation on a curved sky to investigate the correspondence between the convergence peak and the dark matter haloes at the LOS. We find that, in case of no noise and for source galaxies at $z_{\rm s}=1$, more than $65\%$ peaks with $\text{SNR} \geq 3$ (signal to noise ratio) are related to more than one massive haloes with mass larger than $10^{13} {\rm M}_{\odot}$. Those massive haloes contribute $87.2\%$ to high peaks ($\text{SNR} \geq 5$) with the remaining contributions are from the large-scale structures. On the other hand, the peaks distribution is skewed by the noise in galaxy shape measurement, especially for lower SNR peaks. In the noisy field where the shape noise is modelled as a Gaussian distribution, about $60\%$ high peaks ($\text{SNR} \geq 5$) are true peaks and the fraction decreases to $20\%$ for lower peaks ($ 3 \leq \text{SNR} < 5$). Furthermore, we find that high peaks ($\text{SNR} \geq 5$) are dominated by very massive haloes larger than $10^{14} {\rm M}_{\odot}$.

astro-ph.CO↗

arXiv2018

Full-sky ray-tracing simulation of weak lensing using ELUCID simulations: exploring galaxy intrinsic alignment and cosmic shear correlations

The intrinsic alignment of galaxies is an important systematic effect in weak-lensing surveys, which can affect the derived cosmological parameters. One direct way to distinguish different alignment models and quantify their effects on the measurement is to produce mocked weak-lensing surveys. In this work, we use full-sky ray-tracing technique to produce mock images of galaxies from the ELUCID $N$-body simulation run with the WMAP9 cosmology. In our model we assume that the shape of central elliptical galaxy follows that of the dark matter halo, and spiral galaxy follows the halo spin. Using the mocked galaxy images, a combination of galaxy intrinsic shape and the gravitational shear, we compare the predicted tomographic shear correlations to the results of KiDS and DLS. It is found that our predictions stay between the KiDS and DLS results. We rule out a model in which the satellite galaxies are radially aligned with the center galaxy, otherwise the shear-correlations on small scales are too high. Most important, we find that although the intrinsic alignment of spiral galaxies is very weak, they induce a positive correlation between the gravitational shear signal and the intrinsic galaxy orientation (GI). This is because the spiral galaxy is tangentially aligned with the nearby large-scale overdensity, contrary to the radial alignment of elliptical galaxy. Our results explain the origin of detected positive GI term from the weak-lensing surveys. We conclude that in future analysis, the GI model must include the dependence on galaxy types in more detail.

astro-ph.CO↗