arXiv subjects

Ling Chen

Publications and source records attributed to Ling Chen.

At least 181 records · Page 10Linked to original sources

arXiv2021

Generalization in Text-based Games via Hierarchical Reinforcement Learning

Deep reinforcement learning provides a promising approach for text-based games in studying natural language communication between humans and artificial agents. However, the generalization still remains a big challenge as the agents depend critically on the complexity and variety of training tasks. In this paper, we address this problem by introducing a hierarchical framework built upon the knowledge graph-based RL agent. In the high level, a meta-policy is executed to decompose the whole game into a set of subtasks specified by textual goals, and select one of them based on the KG. Then a sub-policy in the low level is executed to conduct goal-conditioned reinforcement learning. We carry out experiments on games with various difficulty levels and show that the proposed method enjoys favorable generalizability.

cs.CL↗

arXiv2021

Group-Aware Graph Neural Network for Nationwide City Air Quality Forecasting

The problem of air pollution threatens public health. Air quality forecasting can provide the air quality index hours or even days later, which can help the public to prevent air pollution in advance. Previous works focus on citywide air quality forecasting and cannot solve nationwide city forecasting problem, whose difficulties lie in capturing the latent dependencies between geographically distant but highly correlated cities. In this paper, we propose the group-aware graph neural network (GAGNN), a hierarchical model for nationwide city air quality forecasting. The model constructs a city graph and a city group graph to model the spatial and latent dependencies between cities, respectively. GAGNN introduces differentiable grouping network to discover the latent dependencies among cities and generate city groups. Based on the generated city groups, a group correlation encoding module is introduced to learn the correlations between them, which can effectively capture the dependencies between city groups. After the graph construction, GAGNN implements message passing mechanism to model the dependencies between cities and city groups. The evaluation experiments on Chinese city air quality dataset indicate that our GAGNN outperforms existing forecasting models.

cs.LG↗

arXiv2021

A General Principle: π-Conjugated Confinement Maximizes Band Gap of DUV NLO Materials

Current nonlinear optical materials face a conventional limitation on the tradeoff between band gap and birefringence, especially in the deep UV spectral region. To circumvent such a dilemma, we propose a general principle, a π-conjugated confinement, to partially decouple the inter group π-conjugated interactions with the separation of a non-π-conjugated group so as to maximize the band gap in comparison with those of simple π-conjugated salts, such as borates, carbonates. Meanwhile, to maintain a large optical anisotropy. We uncover that the π-conjugated confinement is a shared structural feature for all the known DUV NLO materials with favorable properties (45 compounds), and thus, it provides an essential design criterion. Guided by this principle, the carbonophosphate is predicted theoretically for the first time as a promising DUV candidate system, Sr3Y[PO4][CO3]3 and Na3X[PO4][CO3] (X = Ba, Sr, Ca, Mg) exhibit an enhanced birefringence that is 3-24 times larger than that of the simple phosphate, as well as an increased band gap that is 0.2-1.7 eV wider than that of the simple carbonate. Especially, the shortest SHG output of Sr3Y[PO4][CO3]3 is at λPM = 181 nm, being the shortest one among phosphates to date.

cond-mat.mtrl-sci↗

arXiv2021

[Ag(NH3)2]2SO4: A coordination strategy on the cationic-moiety to design nonlinear optical materials

Over decades, guided by the anionic group theory, the majority work has been focused on the anionic-moiety of a nonlinear optical material, however, the property guided structure modification and design on the cationic-moiety has long been neglected. Herein, we report for the first time a coordination strategy on the cationic-moiety, as demonstrated by the first exmple, [Ag(NH3)2]2SO4 vs Ag2SO4, the coordination of the plus one Ag+ cation by the neutral ligand forming the [Ag(NH3)2]+ cationic-moiety drives the formation of the noncentrosymmetric tetragonal P-421c structure which exhibits a remarkable property improvement, including a strong SHG intersity (1.4*KDP vs 0 @1064 nm), and a large birefringence (delta(n)cal.: 0.102 vs 0.012 @1064 nm). Furthermore, we discover that owing to the strong hydrogen bonds and spatial confinement of [SO4]2- anions, the cation [Ag(NH3)2]+ bends parallel to the crystallographic c axis with a bond angle of N-Ag-N = 174.35deg, generating a permenant dipole moment z = -0.12 D that is responsible for the large birefringence that enlarges the range of the phase matching SHG laser output. We believe what we discover is only a glimpse of the long been neglected crystal engineering on the cationic-moiety. Encourage by this work, exciting works on other ionic compound systems shall flood in.

cond-mat.mtrl-sci↗

arXiv2021

Spin glass state in layered compound MnSb2Te4

As a sister compound and isostructural of MnBi2Te4, the high quality MnSb2Te4 single crystals are grown via solid-state reaction where prolonged annealing and narrow temperature window play critical roles on account of its thermal metastability. X-ray diffraction analysis on MnSb2Te4 single crystals reveals pronounced cation intermixing, 28.9(7)% Sb antisite defects on the Mn (3a) site and 19.3(6)% Mn antisite defects on the Sb (6c) site, compared with MnBi2Te4. Unlike antiferromagnetic (AFM) nature MnBi2Te4, MnSb2Te4 contains magnetic and antiferromagnetic competition and exhibits a spin glass (SG) state below 24 K. Its magnetic hysteresis, anisotropy, and relaxation process are investigated in detail with DC and AC magnetization measurements. Moreover, anomalous Hall effect as a p-type conductor is demonstrated through transport measurements. This work grants MnSb2Te4 a possible access to the future exploration of exotic quantum physics by removing the odd/even layer number restraint in intrinsic AFM MnBi2Te4-family materials as a result of the crossover between its magnetism and potential topology in the Sb-Te layer.

cond-mat.mtrl-sci↗

arXiv2021

Homophily Outlier Detection in Non-IID Categorical Data

Most of existing outlier detection methods assume that the outlier factors (i.e., outlierness scoring measures) of data entities (e.g., feature values and data objects) are Independent and Identically Distributed (IID). This assumption does not hold in real-world applications where the outlierness of different entities is dependent on each other and/or taken from different probability distributions (non-IID). This may lead to the failure of detecting important outliers that are too subtle to be identified without considering the non-IID nature. The issue is even intensified in more challenging contexts, e.g., high-dimensional data with many noisy features. This work introduces a novel outlier detection framework and its two instances to identify outliers in categorical data by capturing non-IID outlier factors. Our approach first defines and incorporates distribution-sensitive outlier factors and their interdependence into a value-value graph-based representation. It then models an outlierness propagation process in the value graph to learn the outlierness of feature values. The learned value outlierness allows for either direct outlier detection or outlying feature selection. The graph representation and mining approach is employed here to well capture the rich non-IID characteristics. Our empirical results on 15 real-world data sets with different levels of data complexities show that (i) the proposed outlier detection methods significantly outperform five state-of-the-art methods at the 95%/99% confidence level, achieving 10%-28% AUC improvement on the 10 most complex data sets; and (ii) the proposed feature selection methods significantly outperform three competing methods in enabling subsequent outlier detection of two different existing detectors.

cs.LG↗

arXiv2021

Unified Robust Training for Graph NeuralNetworks against Label Noise

Graph neural networks (GNNs) have achieved state-of-the-art performance for node classification on graphs. The vast majority of existing works assume that genuine node labels are always provided for training. However, there has been very little research effort on how to improve the robustness of GNNs in the presence of label noise. Learning with label noise has been primarily studied in the context of image classification, but these techniques cannot be directly applied to graph-structured data, due to two major challenges -- label sparsity and label dependency -- faced by learning on graphs. In this paper, we propose a new framework, UnionNET, for learning with noisy labels on graphs under a semi-supervised setting. Our approach provides a unified solution for robustly training GNNs and performing label correction simultaneously. The key idea is to perform label aggregation to estimate node-level class probability distributions, which are used to guide sample reweighting and label correction. Compared with existing works, UnionNET has two appealing advantages. First, it requires no extra clean supervision, or explicit estimation of the noise transition matrix. Second, a unified learning framework is proposed to robustly train GNNs in an end-to-end manner. Experimental results show that our proposed approach: (1) is effective in improving model robustness against different types and levels of label noise; (2) yields significant improvements over state-of-the-art baselines.

cs.LG↗

arXiv2020

Deep Reinforcement Learning with Stacked Hierarchical Attention for Text-based Games

We study reinforcement learning (RL) for text-based games, which are interactive simulations in the context of natural language. While different methods have been developed to represent the environment information and language actions, existing RL agents are not empowered with any reasoning capabilities to deal with textual games. In this work, we aim to conduct explicit reasoning with knowledge graphs for decision making, so that the actions of an agent are generated and supported by an interpretable inference procedure. We propose a stacked hierarchical attention mechanism to construct an explicit representation of the reasoning process by exploiting the structure of the knowledge graph. We extensively evaluate our method on a number of man-made benchmark games, and the experimental results demonstrate that our method performs better than existing text-based agents.

cs.LG↗

arXiv2020

Chaos-induced resistivity in different magnetic configurations

It is widely believed that magnetic reconnection plays an important role in various eruptive phenomena of space and astrophysical plasmas. The mechanism of anomalous resistivity, however, has been an open and unsolved problem. The chaos-induced resistivity proposed by Yoshida (1998) is one of possible mechanisms for anomalous resistivity. By use of the test particle simulation, the present work studies the chaos-induced resistivity for different configurations of reconnection magnetic fields and its distribution in different chaos regions of reconnection current sheets. The results show that the chaos-induced resistivity can be 6-7 orders of magnitude higher than the classical Spitzer resistivity in the X-type chaos regions and 5 orders of magnitude in the O-type chaos regions. Moreover, in the X-type chaos regions the chaos-induced resistivity of the magnetized case is higher by a factor of 2 to 3 times than that of the unmagnetized case, but in the O-type chaos regions the chaos-induced resistivity of the magnetized case is close to or lower than that of the unmagnetized case. The present work is helpful to the understanding of the dynamics of reconnection current sheets, especially of the generation mechanism of the anomalous resistivity of collisionless reconnection regions.

physics.plasm-ph↗

arXiv2020

SEAL: Semi-supervised Adversarial Active Learning on Attributed Graphs

Active learning (AL) on attributed graphs has received increasing attention with the prevalence of graph-structured data. Although AL has been widely studied for alleviating label sparsity issues with the conventional non-related data, how to make it effective over attributed graphs remains an open research question. Existing AL algorithms on graphs attempt to reuse the classic AL query strategies designed for non-related data. However, they suffer from two major limitations. First, different AL query strategies calculated in distinct scoring spaces are often naively combined to determine which nodes to be labelled. Second, the AL query engine and the learning of the classifier are treated as two separating processes, resulting in unsatisfactory performance. In this paper, we propose a SEmi-supervised Adversarial active Learning (SEAL) framework on attributed graphs, which fully leverages the representation power of deep neural networks and devises a novel AL query strategy in an adversarial way. Our framework learns two adversarial components: a graph embedding network that encodes both the unlabelled and labelled nodes into a latent space, expecting to trick the discriminator to regard all nodes as already labelled, and a semi-supervised discriminator network that distinguishes the unlabelled from the existing labelled nodes in the latent space. The divergence score, generated by the discriminator in a unified latent space, serves as the informativeness measure to actively select the most informative node to be labelled by an oracle. The two adversarial components form a closed loop to mutually and simultaneously reinforce each other towards enhancing the active learning performance. Extensive experiments on four real-world networks validate the effectiveness of the SEAL framework with superior performance improvements to state-of-the-art baselines.

cs.LG↗

arXiv2020

Histopathology of Third Trimester Placenta from SARS-CoV-2-Positive Women

Background: This study aims to investigate whether maternal SARS-CoV-2 status affect placental pathology. Methods: A retrospective case-control study was conducted by reviewing charts and slides of placentas between April 1 to July 24, 2020. Clinical history of COVID-19 were searched in Pathology Database (CoPath). Controls were matched with SARS-CoV-2-negative women with singleton deliveries in the 3rd-trimester. Individual and group, pathological features were extracted from placental pathology reports. Results: Twenty-one 3rd-trimester, placentas from SARS-CoV-2-positive women were identified and compared to 20 placentas from SARS-CoV-2-negative women. There were no significant differences in individual or group gross or microscopic pathological features between the groups. Within the SARS-CoV-2+ group, there are no differences between symptomatic and asymptomatic women. Conclusion: Placentas from SARS-CoV-2-positive women do not demonstrate a specific pathological pattern. Pregnancy complicated with COVID-19 during the 3rd trimester does not have a demonstrable effect on placental structure and pathology.

q-bio.TO↗

arXiv2020

Recurrent Dirichlet Belief Networks for Interpretable Dynamic Relational Data Modelling

The Dirichlet Belief Network~(DirBN) has been recently proposed as a promising approach in learning interpretable deep latent representations for objects. In this work, we leverage its interpretable modelling architecture and propose a deep dynamic probabilistic framework -- the Recurrent Dirichlet Belief Network~(Recurrent-DBN) -- to study interpretable hidden structures from dynamic relational data. The proposed Recurrent-DBN has the following merits: (1) it infers interpretable and organised hierarchical latent structures for objects within and across time steps; (2) it enables recurrent long-term temporal dependence modelling, which outperforms the one-order Markov descriptions in most of the dynamic probabilistic frameworks. In addition, we develop a new inference strategy, which first upward-and-backward propagates latent counts and then downward-and-forward samples variables, to enable efficient Gibbs sampling for the Recurrent-DBN. We apply the Recurrent-DBN to dynamic relational data problems. The extensive experiment results on real-world data validate the advantages of the Recurrent-DBN over the state-of-the-art models in interpretable latent structure discovery and improved link prediction performance.

cs.LG↗

arXiv2020

Smoothing Graphons for Modelling Exchangeable Relational Data

Modelling exchangeable relational data can be described by \textit{graphon theory}. Most Bayesian methods for modelling exchangeable relational data can be attributed to this framework by exploiting different forms of graphons. However, the graphons adopted by existing Bayesian methods are either piecewise-constant functions, which are insufficiently flexible for accurate modelling of the relational data, or are complicated continuous functions, which incur heavy computational costs for inference. In this work, we introduce a smoothing procedure to piecewise-constant graphons to form {\em smoothing graphons}, which permit continuous intensity values for describing relations, but without impractically increasing computational costs. In particular, we focus on the Bayesian Stochastic Block Model (SBM) and demonstrate how to adapt the piecewise-constant SBM graphon to the smoothed version. We initially propose the Integrated Smoothing Graphon (ISG) which introduces one smoothing parameter to the SBM graphon to generate continuous relational intensity values. We then develop the Latent Feature Smoothing Graphon (LFSG), which improves on the ISG by introducing auxiliary hidden labels to decompose the calculation of the ISG intensity and enable efficient inference. Experimental results on real-world data sets validate the advantages of applying smoothing strategies to the Stochastic Block Model, demonstrating that smoothing graphons can greatly improve AUC and precision for link prediction without increasing computational complexity.

stat.ML↗

arXiv2020

Relational State-Space Model for Stochastic Multi-Object Systems

Real-world dynamical systems often consist of multiple stochastic subsystems that interact with each other. Modeling and forecasting the behavior of such dynamics are generally not easy, due to the inherent hardness in understanding the complicated interactions and evolutions of their constituents. This paper introduces the relational state-space model (R-SSM), a sequential hierarchical latent variable model that makes use of graph neural networks (GNNs) to simulate the joint state transitions of multiple correlated objects. By letting GNNs cooperate with SSM, R-SSM provides a flexible way to incorporate relational information into the modeling of multi-object dynamics. We further suggest augmenting the model with normalizing flows instantiated for vertex-indexed random variables and propose two auxiliary contrastive objectives to facilitate the learning. The utility of R-SSM is empirically evaluated on synthetic and real time-series datasets.

cs.LG↗

arXiv2019

Multi-Range Attentive Bicomponent Graph Convolutional Network for Traffic Forecasting

Traffic forecasting is of great importance to transportation management and public safety, and very challenging due to the complicated spatial-temporal dependency and essential uncertainty brought about by the road network and traffic conditions. Latest studies mainly focus on modeling the spatial dependency by utilizing graph convolutional networks (GCNs) throughout a fixed weighted graph. However, edges, i.e., the correlations between pair-wise nodes, are much more complicated and interact with each other. In this paper, we propose the Multi-Range Attentive Bicomponent GCN (MRA-BGCN), a novel deep learning model for traffic forecasting. We first build the node-wise graph according to the road network distance and the edge-wise graph according to various edge interaction patterns. Then, we implement the interactions of both nodes and edges using bicomponent graph convolution. The multi-range attention mechanism is introduced to aggregate information in different neighborhood ranges and automatically learn the importance of different ranges. Extensive experiments on two real-world road network traffic datasets, METR-LA and PEMS-BAY, show that our MRA-BGCN achieves the state-of-the-art results.

cs.LG↗

arXiv2019

Scalable Deep Generative Relational Models with High-Order Node Dependence

We propose a probabilistic framework for modelling and exploring the latent structure of relational data. Given feature information for the nodes in a network, the scalable deep generative relational model (SDREM) builds a deep network architecture that can approximate potential nonlinear mappings between nodes' feature information and the nodes' latent representations. Our contribution is two-fold: (1) We incorporate high-order neighbourhood structure information to generate the latent representations at each node, which vary smoothly over the network. (2) Due to the Dirichlet random variable structure of the latent representations, we introduce a novel data augmentation trick which permits efficient Gibbs sampling. The SDREM can be used for large sparse networks as its computational cost scales with the number of positive links. We demonstrate its competitive performance through improved link prediction performance on a range of real-world datasets.

stat.ML↗

arXiv2018

Personalized Video Recommendation Using Rich Contents from Videos

Video recommendation has become an essential way of helping people explore the massive videos and discover the ones that may be of interest to them. In the existing video recommender systems, the models make the recommendations based on the user-video interactions and single specific content features. When the specific content features are unavailable, the performance of the existing models will seriously deteriorate. Inspired by the fact that rich contents (e.g., text, audio, motion, and so on) exist in videos, in this paper, we explore how to use these rich contents to overcome the limitations caused by the unavailability of the specific ones. Specifically, we propose a novel general framework that incorporates arbitrary single content feature with user-video interactions, named as collaborative embedding regression (CER) model, to make effective video recommendation in both in-matrix and out-of-matrix scenarios. Our extensive experiments on two real-world large-scale datasets show that CER beats the existing recommender models with any single content feature and is more time efficient. In addition, we propose a priority-based late fusion (PRI) method to gain the benefit brought by the integrating the multiple content features. The corresponding experiment shows that PRI brings real performance improvement to the baseline and outperforms the existing fusion methods.

cs.IR↗

arXiv2018

A Review for Weighted MinHash Algorithms

Data similarity (or distance) computation is a fundamental research topic which underpins many high-level applications based on similarity measures in machine learning and data mining. However, in large-scale real-world scenarios, the exact similarity computation has become daunting due to "3V" nature (volume, velocity and variety) of big data. In such cases, the hashing techniques have been verified to efficiently conduct similarity estimation in terms of both theory and practice. Currently, MinHash is a popular technique for efficiently estimating the Jaccard similarity of binary sets and furthermore, weighted MinHash is generalized to estimate the generalized Jaccard similarity of weighted sets. This review focuses on categorizing and discussing the existing works of weighted MinHash algorithms. In this review, we mainly categorize the Weighted MinHash algorithms into quantization-based approaches, "active index"-based ones and others, and show the evolution and inherent connection of the weighted MinHash algorithms, from the integer weighted MinHash algorithms to real-valued weighted MinHash ones (particularly the Consistent Weighted Sampling scheme). Also, we have developed a python toolbox for the algorithms, and released it in our github. Based on the toolbox, we experimentally conduct a comprehensive comparative study of the standard MinHash algorithm and the weighted MinHash ones.

cs.DS↗