arXiv subjects

Tong Zhao

Publications and source records attributed to Tong Zhao.

At least 181 records · Page 10Linked to original sources

arXiv2020

Learning Attribute-Structure Co-Evolutions in Dynamic Graphs

Most graph neural network models learn embeddings of nodes in static attributed graphs for predictive analysis. Recent attempts have been made to learn temporal proximity of the nodes. We find that real dynamic attributed graphs exhibit complex co-evolution of node attributes and graph structure. Learning node embeddings for forecasting change of node attributes and birth and death of links over time remains an open problem. In this work, we present a novel framework called CoEvoGNN for modeling dynamic attributed graph sequence. It preserves the impact of earlier graphs on the current graph by embedding generation through the sequence. It has a temporal self-attention mechanism to model long-range dependencies in the evolution. Moreover, CoEvoGNN optimizes model parameters jointly on two dynamic tasks, attribute inference and link prediction over time. So the model can capture the co-evolutionary patterns of attribute change and link formation. This framework can adapt to any graph neural algorithms so we implemented and investigated three methods based on it: CoEvoGCN, CoEvoGAT, and CoEvoSAGE. Experiments demonstrate the framework (and its methods) outperform strong baselines on predicting an entire unseen graph snapshot of personal attributes and interpersonal links in dynamic social graphs and financial graphs.

cs.LG↗

arXiv2020

AutoKnow: Self-Driving Knowledge Collection for Products of Thousands of Types

Can one build a knowledge graph (KG) for all products in the world? Knowledge graphs have firmly established themselves as valuable sources of information for search and question answering, and it is natural to wonder if a KG can contain information about products offered at online retail sites. There have been several successful examples of generic KGs, but organizing information about products poses many additional challenges, including sparsity and noise of structured data for products, complexity of the domain with millions of product types and thousands of attributes, heterogeneity across large number of categories, as well as large and constantly growing number of products. We describe AutoKnow, our automatic (self-driving) system that addresses these challenges. The system includes a suite of novel techniques for taxonomy construction, product property identification, knowledge extraction, anomaly detection, and synonym discovery. AutoKnow is (a) automatic, requiring little human intervention, (b) multi-scalable, scalable in multiple dimensions (many domains, many products, and many attributes), and (c) integrative, exploiting rich customer behavior logs. AutoKnow has been operational in collecting product knowledge for over 11K product types.

cs.AI↗

arXiv2020

MultiImport: Inferring Node Importance in a Knowledge Graph from Multiple Input Signals

Given multiple input signals, how can we infer node importance in a knowledge graph (KG)? Node importance estimation is a crucial and challenging task that can benefit a lot of applications including recommendation, search, and query disambiguation. A key challenge towards this goal is how to effectively use input from different sources. On the one hand, a KG is a rich source of information, with multiple types of nodes and edges. On the other hand, there are external input signals, such as the number of votes or pageviews, which can directly tell us about the importance of entities in a KG. While several methods have been developed to tackle this problem, their use of these external signals has been limited as they are not designed to consider multiple signals simultaneously. In this paper, we develop an end-to-end model MultiImport, which infers latent node importance from multiple, potentially overlapping, input signals. MultiImport is a latent variable model that captures the relation between node importance and input signals, and effectively learns from multiple signals with potential conflicts. Also, MultiImport provides an effective estimator based on attentive graph neural networks. We ran experiments on real-world KGs to show that MultiImport handles several challenges involved with inferring node importance from multiple input signals, and consistently outperforms existing methods, achieving up to 23.7% higher NDCG@100 than the state-of-the-art method.

cs.LG↗

arXiv2020

Octet: Online Catalog Taxonomy Enrichment with Self-Supervision

Taxonomies have found wide applications in various domains, especially online for item categorization, browsing, and search. Despite the prevalent use of online catalog taxonomies, most of them in practice are maintained by humans, which is labor-intensive and difficult to scale. While taxonomy construction from scratch is considerably studied in the literature, how to effectively enrich existing incomplete taxonomies remains an open yet important research question. Taxonomy enrichment not only requires the robustness to deal with emerging terms but also the consistency between existing taxonomy structure and new term attachment. In this paper, we present a self-supervised end-to-end framework, Octet, for Online Catalog Taxonomy EnrichmenT. Octet leverages heterogeneous information unique to online catalog taxonomies such as user queries, items, and their relations to the taxonomy nodes while requiring no other supervision than the existing taxonomies. We propose to distantly train a sequence labeling model for term extraction and employ graph neural networks (GNNs) to capture the taxonomy structure as well as the query-item-taxonomy interactions for term attachment. Extensive experiments in different online domains demonstrate the superiority of Octet over state-of-the-art methods via both automatic and human evaluations. Notably, Octet enriches an online catalog taxonomy in production to 2 times larger in the open-world evaluation.

cs.CL↗

arXiv2020

Canonicalizing Open Knowledge Bases with Multi-Layered Meta-Graph Neural Network

Noun phrases and relational phrases in Open Knowledge Bases are often not canonical, leading to redundant and ambiguous facts. In this work, we integrate structural information (from which tuple, which sentence) and semantic information (semantic similarity) to do the canonicalization. We represent the two types of information as a multi-layered graph: the structural information forms the links across the sentence, relational phrase, and noun phrase layers; the semantic information forms weighted intra-layer links for each layer. We propose a graph neural network model to aggregate the representations of noun phrases and relational phrases through the multi-layered meta-graph structure. Experiments show that our model outperforms existing approaches on a public datasets in general domain.

cs.CL↗

arXiv2020

A Probabilistic Model with Commonsense Constraints for Pattern-based Temporal Fact Extraction

Textual patterns (e.g., Country's president Person) are specified and/or generated for extracting factual information from unstructured data. Pattern-based information extraction methods have been recognized for their efficiency and transferability. However, not every pattern is reliable: A major challenge is to derive the most complete and accurate facts from diverse and sometimes conflicting extractions. In this work, we propose a probabilistic graphical model which formulates fact extraction in a generative process. It automatically infers true facts and pattern reliability without any supervision. It has two novel designs specially for temporal facts: (1) it models pattern reliability on two types of time signals, including temporal tag in text and text generation time; (2) it models commonsense constraints as observable variables. Experimental results demonstrate that our model significantly outperforms existing methods on extracting true temporal facts from news data.

cs.CL↗

arXiv2020

Fast And Efficient Boolean Matrix Factorization By Geometric Segmentation

Boolean matrix has been used to represent digital information in many fields, including bank transaction, crime records, natural language processing, protein-protein interaction, etc. Boolean matrix factorization (BMF) aims to find an approximation of a binary matrix as the Boolean product of two low rank Boolean matrices, which could generate vast amount of information for the patterns of relationships between the features and samples. Inspired by binary matrix permutation theories and geometric segmentation, we developed a fast and efficient BMF approach called MEBF (Median Expansion for Boolean Factorization). Overall, MEBF adopted a heuristic approach to locate binary patterns presented as submatrices that are dense in 1's. At each iteration, MEBF permutates the rows and columns such that the permutated matrix is approximately Upper Triangular-Like (UTL) with so-called Simultaneous Consecutive-ones Property (SC1P). The largest submatrix dense in 1 would lies on the upper triangular area of the permutated matrix, and its location was determined based on a geometric segmentation of a triangular. We compared MEBF with other state of the art approaches on data scenarios with different sparsity and noise levels. MEBF demonstrated superior performances in lower reconstruction error, and higher computational efficiency, as well as more accurate sparse patterns than popular methods such as ASSO, PANDA and MP. We demonstrated the application of MEBF on both binary and non-binary data sets, and revealed its further potential in knowledge retrieving and data denoising.

cs.LG↗

arXiv2019

Evaluating entropy rate of laser chaos and shot noise

Evaluating entropy rate of high-dimensional chaos and shot noise from analog raw signals remains elusive and important in information security. We experimentally present an accurate assessment of entropy rate for physical process randomness. The entropy generation of optical-feedback laser chaos and physical randomness limit from shot noise are quantified and unambiguously discriminated using the growth rate of average permutation entropy value in memory time. The permutation entropy difference of filtered laser chaos with varying embedding delay time is investigated experimentally and theoretically. High resolution maps of the entropy difference is observed over the range of the injection-feedback parameter space. We also clarify an inverse relationship between the entropy rate and time delay signature of laser chaos over a wide range of parameters. Compared to the original chaos, the time delay signature is suppressed up to 95% with the minimum of 0.015 via frequency-band extractor, and the experiment agrees well with the theory. Our system provides a commendable entropy evaluation and source for physical random number generation.

physics.optics↗

arXiv2019

Do the current astronomical observations exclude the existence of non-strange quark stars?

As is pointed out in a recent work (Phys. Rev. Lett. 120, 222001), quark matter may not be strange. Inspired by this argument, we use a new self-consistent mean field approximation method to study the equation of state of cold dense matter within the framework of the two-flavor NJL model. Then the mass-radius relationship of two-flavor pure quark stars is studied. In the new self-consistent mean field approximation method we introduced, there is a free parameter $α$, which reflects the weight of different interaction channels. In principal, $α$ should be determined by experiments rather than the self-consistent mean field approximation itself. In this paper, thus, the influence of the variation of $α$ on the critical chemical potential of chiral phase transition and the stiffness of the EOS are thoroughly explored. It is found that the stiffness of EOS can be increased greatly to support a two-solar-mass pure quark star when $α$ is greater than 0.95. This means that current theoretical calculations and astronomical observations cannot rule out the possibility of a two-flavor pure quark star.

nucl-th↗

arXiv2019

Constructing Information-Lossless Biological Knowledge Graphs from Conditional Statements

Conditions are essential in the statements of biological literature. Without the conditions (e.g., environment, equipment) that were precisely specified, the facts (e.g., observations) in the statements may no longer be valid. One biological statement has one or multiple fact(s) and/or condition(s). Their subject and object can be either a concept or a concept's attribute. Existing information extraction methods do not consider the role of condition in the biological statement nor the role of attribute in the subject/object. In this work, we design a new tag schema and propose a deep sequence tagging framework to structure conditional statement into fact and condition tuples from biological text. Experiments demonstrate that our method yields a information-lossless structure of the literature.

cs.CL↗

arXiv2019

Estimating Node Importance in Knowledge Graphs Using Graph Neural Networks

How can we estimate the importance of nodes in a knowledge graph (KG)? A KG is a multi-relational graph that has proven valuable for many tasks including question answering and semantic search. In this paper, we present GENI, a method for tackling the problem of estimating node importance in KGs, which enables several downstream applications such as item recommendation and resource allocation. While a number of approaches have been developed to address this problem for general graphs, they do not fully utilize information available in KGs, or lack flexibility needed to model complex relationship between entities and their importance. To address these limitations, we explore supervised machine learning algorithms. In particular, building upon recent advancement of graph neural networks (GNNs), we develop GENI, a GNN-based method designed to deal with distinctive challenges involved with predicting node importance in KGs. Our method performs an aggregation of importance scores instead of aggregating node embeddings via predicate-aware attention mechanism and flexible centrality adjustment. In our evaluation of GENI and existing methods on predicting node importance in real-world KGs with different characteristics, GENI achieves 5-17% higher NDCG@100 than the state of the art.

cs.LG↗

arXiv2019

Geometry Effect on Black Body Radiation with Different Boundary Conditions

We study the black body radiation in cavities of different geometry with different boundary conditions, and the formulas of energy spectral densities in films and rods are obtained, also the approximate energy spectral densities in cubic boxes are calculated. We find that the energy spectral densities deviate from Planck's formula greatly when the length(s) at some directions of the cavity can be compared to the typical wavelengths of black body radiation in infinite volume and the boundary conditions also affect the results. We obtain an asymptotic formula of energy spectral density for a closed cavity with Dirichlet boundary condition and find it still fails when the size of the cavity is too small.

quant-ph↗

arXiv2018

Limit of 1-Dimensional Mixed-Mechanism Interacting Particle System Model

Elaborating on the model from voter process with mixed-mechanism under suitable scaling, I have two new mechanisms which are random switch and unbiased local Homogenization and subtly biased advantage but with state dependent coefficient involved. The most crucial one, the existence of high-frequency duplication generating the diffusion term and noise term in each case identifies the limit equation as SPDE driven by space time white noise.

math.PR↗

arXiv2017

Studies of the hybrid star structure within 2+1 flavors NJL model

In this paper we use the equation of state (EOS) of 2+1 flavors Nambu-Jona-Lasinio (NJL) model to study the structure of compact stars. To avoid the ultraviolet divergence, we employ the proper-time regularization (PTR) with an ultraviolet cutoff. For comparison, we fix three sets of parameters, where the constraints of chemical equilibrium and electric charge neutrality conditions are taken into consideration. With a certain interpolation method in the crossover region, we construct three corresponding hybrid EOSs but find that the maximum masses of hybrid stars in the three different cases don't differ too much. It should be pointed out that, the results we get are in accordance with the recent astro-observation PSR J0348+0432, PSR J1614-2230, PSR J1946+3417.

hep-ph↗

arXiv2017

Time delay signature elimination of chaos in a semiconductor laser by dispersive feedback from a chirped FBG

Time delay signature (TDS) of a semiconductor laser subject to dispersive optical feedback from a chirped fiber Bragg grating (CFBG) is investigated experimentally and numerically. Different from mirror, CFBG provides additional frequency-dependent delay caused by dispersion, and thus induces external-cavity modes with irregular mode separation rather than a fixed separation induced by mirror feedback. Compared with mirror feedback, the CFBG feedback can greatly depress and even eliminate the TDS, although it leads to a similar quasi-period route to chaos with increases of feedback. In experiments, by using a CFBG with dispersion of 2000ps/nm, the TDS is decreased by 90% to about 0.04 compared with mirror feedback. Furthermore, both numerical and experimental results show that the TDS evolution is quite different: the TDS decreases more quickly down to a lower plateau (even background noise level of autocorrelation function) and never rises again. This evolution tendency is also different from that of FBG feedback, of which the TDS first decreases to a minimal value and then increases again as feedback strength increases. In addition, the CFBG feedback has no filtering effects and does not require amplification for feedback light.

physics.optics↗

arXiv2016

GT-SEER: Geo-Temporal SEquential Embedding Rank for Point-of-interest Recommendation

Point-of-interest (POI) recommendation is an important application in location-based social networks (LBSNs), which learns the user preference and mobility pattern from check-in sequences to recommend POIs. However, previous POI recommendation systems model check-in sequences based on either tensor factorization or Markov chain model, which cannot capture contextual check-in information in sequences. The contextual check-in information implies the complementary functions among POIs that compose an individual's daily check-in sequence. In this paper, we exploit the embedding learning technique to capture the contextual check-in information and further propose the \textit{\textbf{SE}}quential \textit{\textbf{E}}mbedding \textit{\textbf{R}}ank (\textit{SEER}) model for POI recommendation. In particular, the \textit{SEER} model learns user preferences via a pairwise ranking model under the sequential constraint modeled by the POI embedding learning method. Furthermore, we incorporate two important factors, i.e., temporal influence and geographical influence, into the \textit{SEER} model to enhance the POI recommendation system. Due to the temporal variance of sequences on different days, we propose a temporal POI embedding model and incorporate the temporal POI representations into a temporal preference ranking model to establish the \textit{T}emporal \textit{SEER} (\textit{T-SEER}) model. In addition, We incorporate the geographical influence into the \textit{T-SEER} model and develop the \textit{\textbf{Geo-Temporal}} \textit{\textbf{SEER}} (\textit{GT-SEER}) model.

cs.IR↗

arXiv2016

Performance Analysis of Joint Time Delay and Doppler-Stretch Estimation with Random Stepped-Frequency Signals

This paper investigates the performance of joint time delay and Doppler-stretch estimation with the random stepp ed-frequency (RSF) signal. Applying the ambiguity function (AF) to implement the estimation, we derive the compact expressions of the theoretical mean square errors (MSEs) under high signal-to-noise ratios (SNRs). The obtained MSEs are shown consistent with the corresponding Cramer-Rao lower bounds (CRLBs), implying that the AF-based estimation is approximately efficient. Waveform parameters including higher carrier frequencies, wider bandwidth covered by the carrier frequencies, and frequency shifting codewords with larger variance are expected for a better estimation performance. As a synthetic wideband signal, the RSF signal achieves the same estimation performance as the OFDM signal within an identical bandwidth. Due to its instantaneous narrowband character, requirement for the bandwidth of the receiver is much reduced.

cs.IT↗

arXiv2016

Saliency Detection with Spaces of Background-based Distribution

In this letter, an effective image saliency detection method is proposed by constructing some novel spaces to model the background and redefine the distance of the salient patches away from the background. Concretely, given the backgroundness prior, eigendecomposition is utilized to create four spaces of background-based distribution (SBD) to model the background, in which a more appropriate metric (Mahalanobis distance) is quoted to delicately measure the saliency of every image patch away from the background. After that, a coarse saliency map is obtained by integrating the four adjusted Mahalanobis distance maps, each of which is formed by the distances between all the patches and background in the corresponding SBD. To be more discriminative, the coarse saliency map is further enhanced into the posterior probability map within Bayesian perspective. Finally, the final saliency map is generated by properly refining the posterior probability map with geodesic distance. Experimental results on two usual datasets show that the proposed method is effective compared with the state-of-the-art algorithms.

cs.CV↗