Searcharxiv⌕ Search

arXiv subjects

Wenjie Zhang

Publications and source records attributed to Wenjie Zhang.

At least 217 records · Page 12Linked to original sources
arXiv2020

Exploring Cohesive Subgraphs with Vertex Engagement and Tie Strength in Bipartite Graphs

We propose a novel cohesive subgraph model called $τ$-strengthened $(α,β)$-core (denoted as $(α,β)_τ$-core), which is the first to consider both tie strength and vertex engagement on bipartite graphs. An edge is a strong tie if contained in at least $τ$ butterflies ($2\times2$-bicliques). $(α,β)_τ$-core requires each vertex on the upper or lower level to have at least $α$ or $β$ strong ties, given strength level $τ$. To retrieve the vertices of $(α,β)_τ$-core optimally, we construct index $I_{α,β,τ}$ to store all $(α,β)_τ$-cores. Effective optimization techniques are proposed to improve index construction. To make our idea practical on large graphs, we propose 2D-indexes $I_{α,β}, I_{β,τ}$, and $I_{α,τ}$ that selectively store the vertices of $(α,β)_τ$-core for some $α,β$, and $τ$. The 2D-indexes are more space-efficient and require less construction time, each of which can support $(α,β)_τ$-core queries. As query efficiency depends on input parameters and the choice of 2D-index, we propose a learning-based hybrid computation paradigm by training a feed-forward neural network to predict the optimal choice of 2D-index that minimizes the query time. Extensive experiments show that ($1$) $(α,β)_τ$-core is an effective model capturing unique and important cohesive subgraphs; ($2$) the proposed techniques significantly improve the efficiency of index construction and query processing.

cs.SI↗
arXiv2020

AOT: Pushing the Efficiency Boundary of Main-memory Triangle Listing

Triangle listing is an important topic significant in many practical applications. Efficient algorithms exist for the task of triangle listing. Recent algorithms leverage an orientation framework, which can be thought of as mapping an undirected graph to a directed acylic graph, namely oriented graph, with respect to any global vertex order. In this paper, we propose an adaptive orientation technique that satisfies the orientation technique but refines it by traversing carefully based on the out-degree of the vertices in the oriented graph during the computation of triangles. Based on this adaptive orientation technique, we design a new algorithm, namely aot, to enhance the edge-iterator listing paradigm. We also make improvements to the performance of aot by exploiting the local order within the adjacent list of the vertices. We show that aot is the first work which can achieve best performance in terms of both practical performance and theoretical time complexity. Our comprehensive experiments over $16$ real-life large graphs show a superior performance of our \aot algorithm when compared against the state-of-the-art, especially for massive graphs with billions of edges. Theoretically, we show that our proposed algorithm has a time complexity of $Θ(\sum_{ \langle u,v \rangle \in \vec{E} } \min\{ deg^{+}(u),deg^{+}(v)\}))$, where $\vec{E}$ and $deg^{+}(x)$ denote the set of directed edges in an oriented graph and the out-degree of vertex $x$ respectively. As to our best knowledge, this is the best time complexity among in-memory triangle listing algorithms.

cs.DB↗
arXiv2020

Efficient Matrix Factorization on Heterogeneous CPU-GPU Systems

Matrix Factorization (MF) has been widely applied in machine learning and data mining. A large number of algorithms have been studied to factorize matrices. Among them, stochastic gradient descent (SGD) is a commonly used method. Heterogeneous systems with multi-core CPUs and GPUs have become more and more promising recently due to the prevalence of GPUs in general-purpose data-parallel applications. Due to the large computational cost of MF, we aim to improve the efficiency of SGD-based MF computation by utilizing the massive parallel processing power of heterogeneous multiprocessors. The main challenge in parallel SGD algorithms on heterogeneous CPU-GPU systems lies in the granularity of the matrix division and the strategy to assign tasks. We design a novel strategy to divide the matrix into a set of blocks by considering two aspects. First, we observe that the matrix should be divided nonuniformly, and relatively large blocks should be assigned to GPUs to saturate the computing power of GPUs. In addition to exploiting the characteristics of hardware, the workloads assigned to two types of hardware should be balanced. Aiming at the final division strategy, we design a cost model tailored for our problem to accurately estimate the performance of hardware on different data sizes. A dynamic scheduling policy is also used to further balance workloads in practice. Extensive experiments show that our proposed algorithm achieves high efficiency with a high quality of training quality.

cs.DC↗
arXiv2020

Terahertz emission in the van der Waals magnet CrSiTe3

The van der Waals magnet CrSiTe3 (CST) has captured immense interest because it is capable of retaining the long-range ferromagnetic order even in its monolayer form, thus offering potential use in spintronic devices. Bulk CST crystal has inversion symmetry that is broken on the crystal surface. Here, by employing ultrafast terahertz (THz) emission spectroscopy and time resolved THz spectroscopy, the THz emission of the CST crystal was investigated, which shows a strong THz emission from the crystal surface under femtosecond (fs) pulse excitation at 800 nm. Theoretical analysis based on space symmetry of CST suggests the dominant role of shift current occurring on the surface with a thickness of a few quintuple layers in producing the THz emission, in consistence with the experimental observation that the emitted THz amplitude strongly depends on the azimuthal and pumping polarization angles. The present study offers a new efficient THz emitter as well as a better understanding of the nonlinear optical response of CST. It hopefully will open a window toward the investigation on the nonlinear optical response in the mono-/few-layer van der Waals crystals with low-dimensional magnetism.

physics.optics↗
arXiv2020

Knowledge-guided Deep Reinforcement Learning for Interactive Recommendation

Interactive recommendation aims to learn from dynamic interactions between items and users to achieve responsiveness and accuracy. Reinforcement learning is inherently advantageous for coping with dynamic environments and thus has attracted increasing attention in interactive recommendation research. Inspired by knowledge-aware recommendation, we proposed Knowledge-Guided deep Reinforcement learning (KGRL) to harness the advantages of both reinforcement learning and knowledge graphs for interactive recommendation. This model is implemented upon the actor-critic network framework. It maintains a local knowledge network to guide decision-making and employs the attention mechanism to capture long-term semantics between items. We have conducted comprehensive experiments in a simulated online environment with six public real-world datasets and demonstrated the superiority of our model over several state-of-the-art methods.

cs.IR↗
arXiv2020

Observation of a thermoelectric Hall plateau in the extreme quantum limit

The thermoelectric Hall effect is the generation of a transverse heat current upon applying an electric field in the presence of a magnetic field. Here we demonstrate that the thermoelectric Hall conductivity $α_{xy}$ in the three-dimensional Dirac semimetal ZrTe$_5$ acquires a robust plateau in the extreme quantum limit of magnetic field. The plateau value is independent of the field strength, disorder strength, carrier concentration, or carrier sign. We explain this plateau theoretically and show that it is a unique signature of three-dimensional Dirac or Weyl electrons in the extreme quantum limit. We further find that other thermoelectric coefficients, such as the thermopower and Nernst coefficient, are greatly enhanced over their zero-field values even at relatively low fields.

cond-mat.mtrl-sci↗
arXiv2020

Efficient Bitruss Decomposition for Large-scale Bipartite Graphs

Cohesive subgraph mining in bipartite graphs becomes a popular research topic recently. An important structure k-bitruss is the maximal cohesive subgraph where each edge is contained in at least k butterflies (i.e., (2, 2)-bicliques). In this paper, we study the bitruss decomposition problem which aims to find all the k-bitrusses for k >= 0. The existing bottom-up techniques need to iteratively peel the edges with the lowest butterfly support. In this peeling process, these techniques are time-consuming to enumerate all the supporting butterflies for each edge. To relax this issue, we first propose a novel online index -- the BE-Index which compresses butterflies into k-blooms (i.e., (2, k)-bicliques). Based on the BE-Index, the new bitruss decomposition algorithm BiT-BU is proposed, along with two batch-based optimizations, to accomplish the butterfly enumeration of the peeling process in an efficient way. Furthermore, the BiT-PC algorithm is devised which is more efficient against handling the edges with high butterfly supports. We theoretically show that our new algorithms significantly reduce the time complexities of the existing algorithms. Also, we conduct extensive experiments on real datasets and the result demonstrates that our new techniques can speed up the state-of-the-art techniques by up to two orders of magnitude.

cs.DB↗
arXiv2019

Heterogeneous Graph-based Knowledge Transfer for Generalized Zero-shot Learning

Generalized zero-shot learning (GZSL) tackles the problem of learning to classify instances involving both seen classes and unseen ones. The key issue is how to effectively transfer the model learned from seen classes to unseen classes. Existing works in GZSL usually assume that some prior information about unseen classes are available. However, such an assumption is unrealistic when new unseen classes appear dynamically. To this end, we propose a novel heterogeneous graph-based knowledge transfer method (HGKT) for GZSL, agnostic to unseen classes and instances, by leveraging graph neural network. Specifically, a structured heterogeneous graph is constructed with high-level representative nodes for seen classes, which are chosen through Wasserstein barycenter in order to simultaneously capture inter-class and intra-class relationship. The aggregation and embedding functions can be learned through graph neural network, which can be used to compute the embeddings of unseen classes by transferring the knowledge from their neighbors. Extensive experiments on public benchmark datasets show that our method achieves state-of-the-art results.

cs.LG↗
arXiv2019

Know Your Mind: Adaptive Brain Signal Classification with Reinforced Attentive Convolutional Neural Networks

Electroencephalography (EEG) signals reflect activities on certain brain areas. Effective classification of time-varying EEG signals is still challenging. First, EEG signal processing and feature engineering are time-consuming and highly rely on expert knowledge. In addition, most existing studies focus on domain-specific classification algorithms which may not be applicable to other domains. Moreover, the EEG signal usually has a low signal-to-noise ratio and can be easily corrupted. In this regard, we propose a generic EEG signal classification framework that accommodates a wide range of applications to address the aforementioned issues. The proposed framework develops a reinforced selective attention model to automatically choose the distinctive information among the raw EEG signals. A convolutional mapping operation is employed to dynamically transform the selected information to an over-complete feature space, wherein implicit spatial dependency of EEG samples distribution is able to be uncovered. We demonstrate the effectiveness of the proposed framework using three representative scenarios: intention recognition with motor imagery EEG, person identification, and neurological diagnosis. Three widely used public datasets and a local dataset are used for our evaluation. The experiments show that our framework outperforms the state-of-the-art baselines and achieves the accuracy of more than 97% on all the datasets with low latency and good resilience of handling complex EEG signals across various domains. These results confirm the suitability of the proposed generic approach for a range of problems in the realm of Brain-Computer Interface applications.

cs.HC↗
arXiv2019

A Survey of Community Search Over Big Graphs

With the rapid development of information technologies, various big graphs are prevalent in many real applications (e.g., social media and knowledge bases). An important component of these graphs is the network community. Essentially, a community is a group of vertices which are densely connected internally. Community retrieval can be used in many real applications, such as event organization, friend recommendation, and so on. Consequently, how to efficiently find high-quality communities from big graphs is an important research topic in the era of big data. Recently a large group of research works, called community search, have been proposed. They aim to provide efficient solutions for searching high-quality communities from large networks in real-time. Nevertheless, these works focus on different types of graphs and formulate communities in different manners, and thus it is desirable to have a comprehensive review of these works. In this survey, we conduct a thorough review of existing community search works. Moreover, we analyze and compare the quality of communities under their models, and the performance of different solutions. Furthermore, we point out new research directions. This survey does not only help researchers to have a better understanding of existing community search solutions, but also provides practitioners a better judgment on choosing the proper solutions.

cs.DB↗
arXiv2019

Efficient Butterfly Counting for Large Bipartite Networks

Bipartite networks are of great importance in many real-world applications. In bipartite networks, butterfly (i.e., a complete 2 x 2 biclique) is the smallest non-trivial cohesive structure and plays a key role. In this paper, we study the problem of efficient counting the number of butterflies in bipartite networks. The most advanced techniques are based on enumerating wedges which is the dominant cost of counting butterflies. Nevertheless, the existing algorithms cannot efficiently handle large-scale bipartite networks. This becomes a bottleneck in large-scale applications. In this paper, instead of the existing layer-priority-based techniques, we propose a vertex-priority-based paradigm BFC-VP to enumerate much fewer wedges; this leads to a significant improvement of the time complexity of the state-of-the-art algorithms. In addition, we present cache-aware strategies to further improve time efficiency while theoretically retaining the time complexity of BFC-VP. Moreover, we also show that our proposed techniques can work efficiently in external and parallel contexts. Our extensive empirical studies demonstrate that the proposed techniques can speed up the state-of-the-art techniques by up to two orders of magnitude for the real datasets.

cs.SI↗
arXiv2019

A Survey and Experimental Analysis of Distributed Subgraph Matching

Recently there emerge many distributed algorithms that aim at solving subgraph matching at scale. Existing algorithm-level comparisons failed to provide a systematic view to the pros and cons of each algorithm mainly due to the intertwining of strategy and optimization. In this paper, we identify four strategies and three general-purpose optimizations from representative state-of-the-art works. We implement the four strategies with the optimizations based on the common Timely dataflow system for systematic strategy-level comparison. Our implementation covers all representation algorithms. We conduct extensive experiments for both unlabelled matching and labelled matching to analyze the performance of distributed subgraph matching under various settings, which is finally summarized as a practical guide.

cs.DB↗
arXiv2019

K-Core Maximization through Edge Additions

A popular model to measure the stability of a network is k-core - the maximal induced subgraph in which every vertex has at least k neighbors. Many studies maximize the number of vertices in k-core to improve the stability of a network. In this paper, we study the edge k-core problem: Given a graph G, an integer k and a budget b, add b edges to non-adjacent vertex pairs in G such that the k-core is maximized. We prove the problem is NP-hard and APX-hard. A heuristic algorithm is proposed on general graphs with effective optimization techniques. Comprehensive experiments on 9 real-life datasets demonstrate the effectiveness and the efficiency of our proposed methods.

cs.SI↗
arXiv2018

Efficient and High-Quality Seeded Graph Matching: Employing High Order Structural Information

Driven by many real applications, we study the problem of seeded graph matching. Given two graphs $G_1 = (V_1, E_1)$ and $G_2 = (V_2, E_2)$, and a small set $S$ of pre-matched node pairs $[u, v]$ where $u \in V_1$ and $v \in V_2$, the problem is to identify a matching between $V_1$ and $V_2$ growing from $S$, such that each pair in the matching corresponds to the same underlying entity. Recent studies on efficient and effective seeded graph matching have drawn a great deal of attention and many popular methods are largely based on exploring the similarity between local structures to identify matching pairs. While these recent techniques work well on random graphs, their accuracy is low over many real networks. Motivated by this, we propose to utilize high order neighboring information to improve the matching accuracy. As a result, a new framework of seeded graph matching is proposed, which employs Personalized PageRank (PPR) to quantify the matching score of each node pair. To further boost the matching accuracy, we propose a novel postponing strategy, which postpones the selection of pairs that have competitors with similar matching scores. We theoretically prove that the postpone strategy indeed significantly improves the matching accuracy. To improve the scalability of matching large graphs, we also propose efficient approximation techniques based on algorithms for computing PPR heavy hitters. Our comprehensive experimental studies on large-scale real datasets demonstrate that, compared with state of the art approaches, our framework not only increases the precision and recall both by a significant margin but also achieves speed-up up to more than one order of magnitude.

cs.DS↗
arXiv2018

V$_5$S$_8$: a Kondo lattice based on intercalation of van der Waals layered transition metal dichalcogenide

Since the discovery of graphene, a tremendous amount of two dimensional (2D) materials have surfaced. Their electronic properties can usually be well understood without considering correlations between electrons. On the other hand, strong electronic correlations are known to give rise to a variety of exotic properties and new quantum phases, for instance, high temperature superconductivity, heavy fermions and quantum spin liquids. The study of these phenomena has been one of the main focuses of condensed matter physics. There is a strong incentive to introduce electronic correlations into 2D materials. Via intercalating a van der Waals layered compound VS$_2$, we show an emergence of a Kondo lattice, an extensively studied strongly correlated system, by magnetic, specific heat, electrical and thermoelectric transport studies. In particular, an exceptionally large Sommerfeld coefficient, 440 mJ$\cdot$K$^{-2}\cdot$mol$^{-1}$, indicates a strong electron correlation. The obtained Kadowaki-Woods ratio, $2.7\times 10^{-6}$ $μΩ\cdot$cm$\cdot$mol$^2\cdot$K$^2\cdot$mJ$^{-2}$, also supports the strong electron-electron interaction. The temperature dependence of the resistivity and thermopower corroborate the Kondo lattice picture. The intercalated compound is one of a few rare examples of $d$-electron Kondo lattices. We further show that the Kondo physics persists in ultra-thin films. This work thus demonstrates a route to generate strong correlations in 2D materials.

cond-mat.mtrl-sci↗
arXiv2018

GB-KMV: An Augmented KMV Sketch for Approximate Containment Similarity Search

In this paper, we study the problem of approximate containment similarity search. Given two records Q and X, the containment similarity between Q and X with respect to Q is |Q intersect X|/ |Q|. Given a query record Q and a set of records S, the containment similarity search finds a set of records from S whose containment similarity regarding Q are not less than the given threshold. This problem has many important applications in commercial and scientific fields such as record matching and domain search. Existing solution relies on the asymmetric LSH method by transforming the containment similarity to well-studied Jaccard similarity. In this paper, we use a different framework by transforming the containment similarity to set intersection. We propose a novel augmented KMV sketch technique, namely GB-KMV, which is data-dependent and can achieve a good trade-off between the sketch size and the accuracy. We provide a set of theoretical analysis to underpin the proposed augmented KMV sketch technique, and show that it outperforms the state-of-the-art technique LSH-E in terms of estimation accuracy under practical assumption. Our comprehensive experiments on real-life datasets verify that GB-KMV is superior to LSH-E in terms of the space-accuracy trade-off, time-accuracy trade-off, and the sketch construction time. For instance, with similar estimation accuracy (F-1 score), GB-KMV is over 100 times faster than LSH-E on some real-life dataset.

cs.IR↗
arXiv2018

Deep Extreme Multi-label Learning

Extreme multi-label learning (XML) or classification has been a practical and important problem since the boom of big data. The main challenge lies in the exponential label space which involves $2^L$ possible label sets especially when the label dimension $L$ is huge, e.g., in millions for Wikipedia labels. This paper is motivated to better explore the label space by originally establishing an explicit label graph. In the meanwhile, deep learning has been widely studied and used in various classification problems including multi-label classification, however it has not been properly introduced to XML, where the label space can be as large as in millions. In this paper, we propose a practical deep embedding method for extreme multi-label classification, which harvests the ideas of non-linear embedding and graph priors-based label space modeling simultaneously. Extensive experiments on public datasets for XML show that our method performs competitive against state-of-the-art result.

cs.LG↗