arXiv subjects

Wook-Shin Han

Publications and source records attributed to Wook-Shin Han.

27 records · Page 2Linked to original sources

arXiv2022

Draft-and-Revise: Effective Image Generation with Contextual RQ-Transformer

Although autoregressive models have achieved promising results on image generation, their unidirectional generation process prevents the resultant images from fully reflecting global contexts. To address the issue, we propose an effective image generation framework of Draft-and-Revise with Contextual RQ-transformer to consider global contexts during the generation process. As a generalized VQ-VAE, RQ-VAE first represents a high-resolution image as a sequence of discrete code stacks. After code stacks in the sequence are randomly masked, Contextual RQ-Transformer is trained to infill the masked code stacks based on the unmasked contexts of the image. Then, Contextual RQ-Transformer uses our two-phase decoding, Draft-and-Revise, and generates an image, while exploiting the global contexts of the image during the generation process. Specifically. in the draft phase, our model first focuses on generating diverse images despite rather low quality. Then, in the revise phase, the model iteratively improves the quality of images, while preserving the global contexts of generated images. In experiments, our method achieves state-of-the-art results on conditional image generation. We also validate that the Draft-and-Revise decoding can achieve high performance by effectively controlling the quality-diversity trade-off in image generation.

cs.CV↗

arXiv2022

Regularizing Attention Networks for Anomaly Detection in Visual Question Answering

For stability and reliability of real-world applications, the robustness of DNNs in unimodal tasks has been evaluated. However, few studies consider abnormal situations that a visual question answering (VQA) model might encounter at test time after deployment in the real-world. In this study, we evaluate the robustness of state-of-the-art VQA models to five different anomalies, including worst-case scenarios, the most frequent scenarios, and the current limitation of VQA models. Different from the results in unimodal tasks, the maximum confidence of answers in VQA models cannot detect anomalous inputs, and post-training of the outputs, such as outlier exposure, is ineffective for VQA models. Thus, we propose an attention-based method, which uses confidence of reasoning between input images and questions and shows much more promising results than the previous methods in unimodal tasks. In addition, we show that a maximum entropy regularization of attention networks can significantly improve the attention-based anomaly detection of the VQA models. Thanks to the simplicity, attention-based anomaly detection and the regularization are model-agnostic methods, which can be used for various cross-modal attentions in the state-of-the-art VQA models. The results imply that cross-modal attention in VQA is important to improve not only VQA accuracy, but also the robustness to various anomalies.

cs.CV↗

arXiv2022

Autoregressive Image Generation using Residual Quantization

For autoregressive (AR) modeling of high-resolution images, vector quantization (VQ) represents an image as a sequence of discrete codes. A short sequence length is important for an AR model to reduce its computational costs to consider long-range interactions of codes. However, we postulate that previous VQ cannot shorten the code sequence and generate high-fidelity images together in terms of the rate-distortion trade-off. In this study, we propose the two-stage framework, which consists of Residual-Quantized VAE (RQ-VAE) and RQ-Transformer, to effectively generate high-resolution images. Given a fixed codebook size, RQ-VAE can precisely approximate a feature map of an image and represent the image as a stacked map of discrete codes. Then, RQ-Transformer learns to predict the quantized feature vector at the next position by predicting the next stack of codes. Thanks to the precise approximation of RQ-VAE, we can represent a 256$\times$256 image as 8$\times$8 resolution of the feature map, and RQ-Transformer can efficiently reduce the computational costs. Consequently, our framework outperforms the existing AR models on various benchmarks of unconditional and conditional image generation. Our approach also has a significantly faster sampling speed than previous AR models to generate high-quality images.

cs.CV↗

arXiv2021

Towards Plug-and-Play Visual Graph Query Interfaces: Data-driven Canned Pattern Selection for Large Networks

Canned patterns (i.e. small subgraph patterns) in visual graph query interfaces (a.k.a GUI) facilitate efficient query formulation by enabling pattern-at-a-time construction mode. However, existing GUIs for querying large networks either do not expose any canned patterns or if they do then they are typically selected manually based on domain knowledge. Unfortunately, manual generation of canned patterns is not only labor intensive but may also lack diversity for supporting efficient visual formulation of a wide range of subgraph queries. In this paper, we present a novel generic and extensible framework called TATTOO that takes a data-driven approach to automatically selecting canned patterns for a GUI from large networks. Specifically, it first decomposes the underlying network into truss-infested and truss-oblivious regions. Then candidate canned patterns capturing different real-world query topologies are generated from these regions. Canned patterns based on a user-specified plug are then selected for the GUI from these candidates by maximizing coverage and diversity, and by minimizing the cognitive load of the pattern set. Experimental studies with real-world datasets demonstrate the benefits of TATTOO. Importantly, this work takes a concrete step towards realizing plug-and-play visual graph query interfaces for large networks.

cs.DB↗

arXiv2021

Symmetric Continuous Subgraph Matching with Bidirectional Dynamic Programming

In many real datasets such as social media streams and cyber data sources, graphs change over time through a graph update stream of edge insertions and deletions. Detecting critical patterns in such dynamic graphs plays an important role in various application domains such as fraud detection, cyber security, and recommendation systems for social networks. Given a dynamic data graph and a query graph, the continuous subgraph matching problem is to find all positive matches for each edge insertion and all negative matches for each edge deletion. The state-of-the-art algorithm TurboFlux uses a spanning tree of a query graph for filtering. However, using the spanning tree may have a low pruning power because it does not take into account all edges of the query graph. In this paper, we present a symmetric and much faster algorithm SymBi which maintains an auxiliary data structure based on a directed acyclic graph instead of a spanning tree, which maintains the intermediate results of bidirectional dynamic programming between the query graph and the dynamic graph. Extensive experiments with real and synthetic datasets show that SymBi outperforms the state-of-the-art algorithm by up to three orders of magnitude in terms of the elapsed time.

cs.DB↗

arXiv2021

[Technical Report] Combining Sampling and Synopses with Worst-Case Optimal Runtime and Quality Guarantees for Graph Pattern Cardinality Estimation

Graph pattern cardinality estimation is the problem of estimating the number of embeddings of a query graph in a data graph. This fundamental problem arises, for example, during query planning in subgraph matching algorithms. There are two major approaches to solving the problem: sampling and synopsis. Synopsis (or summary)-based methods are fast and accurate if synopses capture information of graphs well. However, these methods suffer from large errors due to loss of information during summarization and inherent assumptions. Sampling-based methods are unbiased but suffer from large estimation variance due to large sample space. To address these limitations, we propose Alley, a hybrid method that combines both sampling and synopses. Alley employs 1) a novel sampling strategy, random walk with intersection, which effectively reduces the sample space, 2) branching to further reduce variance, and 3) a novel mining approach that extracts and indexes tangled patterns as synopses which are inherently difficult to estimate by sampling. By using them in the online estimation phase, we can effectively reduce the sample space while still ensuring unbiasedness. We establish that Alley has worst-case optimal runtime and approximation quality guarantees for any given error bound $ε$ and required confidence $μ$. In addition to the theoretical aspect of Alley, our extensive experiments show that Alley outperforms the state-of-the-art methods by up to orders of magnitude higher accuracy with similar efficiency.

cs.DB↗

arXiv2019

Fast and Robust Distributed Subgraph Enumeration

We study the classic subgraph enumeration problem under distributed settings. Existing solutions either suffer from severe memory crisis or rely on large indexes, which makes them impractical for very large graphs. Most of them follow a synchronous model where the performance is often bottlenecked by the machine with the worst performance. Motivated by this, in this paper, we propose RADS, a Robust Asynchronous Distributed Subgraph enumeration system. RADS first identifies results that can be found using single-machine algorithms. This strategy not only improves the overall performance but also reduces network communication and memory cost. Moreover, RADS employs a novel region-grouped multi-round expand verify & filter framework which does not need to shuffle and exchange the intermediate results, nor does it need to replicate a large part of the data graph in each machine. This feature not only reduces network communication cost and memory usage, but also allows us to adopt simple strategies for memory control and load balancing, making it more robust. Several heuristics are also used in RADS to further improve the performance. Our experiments verified the superiority of RADS to state-of-the-art subgraph enumeration approaches.

cs.DB↗

arXiv2015

Taming Subgraph Isomorphism for RDF Query Processing

RDF data are used to model knowledge in various areas such as life sciences, Semantic Web, bioinformatics, and social graphs. The size of real RDF data reaches billions of triples. This calls for a framework for efficiently processing RDF data. The core function of processing RDF data is subgraph pattern matching. There have been two completely different directions for supporting efficient subgraph pattern matching. One direction is to develop specialized RDF query processing engines exploiting the properties of RDF data for the last decade, while the other direction is to develop efficient subgraph isomorphism algorithms for general, labeled graphs for over 30 years. Although both directions have a similar goal (i.e., finding subgraphs in data graphs for a given query graph), they have been independently researched without clear reason. We argue that a subgraph isomorphism algorithm can be easily modified to handle the graph homomorphism, which is the RDF pattern matching semantics, by just removing the injectivity constraint. In this paper, based on the state-of-the-art subgraph isomorphism algorithm, we propose an in-memory solution, TurboHOM++, which is tamed for the RDF processing, and we compare it with the representative RDF processing engines for several RDF benchmarks in a server machine where billions of triples can be loaded in memory. In order to speed up TurboHOM++, we also provide a simple yet effective transformation and a series of optimization techniques. Extensive experiments using several RDF benchmarks show that TurboHOM++ consistently and significantly outperforms the representative RDF engines. Specifically, TurboHOM++ outperforms its competitors by up to five orders of magnitude.

cs.DB↗

arXiv2009

Structural Consistency: Enabling XML Keyword Search to Eliminate Spurious Results Consistently

XML keyword search is a user-friendly way to query XML data using only keywords. In XML keyword search, to achieve high precision without sacrificing recall, it is important to remove spurious results not intended by the user. Efforts to eliminate spurious results have enjoyed some success by using the concepts of LCA or its variants, SLCA and MLCA. However, existing methods still could find many spurious results. The fundamental cause for the occurrence of spurious results is that the existing methods try to eliminate spurious results locally without global examination of all the query results and, accordingly, some spurious results are not consistently eliminated. In this paper, we propose a novel keyword search method that removes spurious results consistently by exploiting the new concept of structural consistency.

cs.DB↗