Alibaba Group

About: Alibaba Group is a company organization based out in Hangzhou, China. It is known for research contribution in the topics: Computer science & Terminal (electronics). The organization has 6810 authors who have published 7389 publications receiving 55653 citations. The organization is also known as: Alibaba Group Holding Limited & Alibaba Group (Cayman Islands).

Toward Achieving Robust Low-Level and High-Level Scene Parsing

Abstract: In this paper, we address the challenging task of scene segmentation. We first discuss and compare two widely used approaches to retain detailed spatial information from pre-trained convolutional context network (CNN)—“dilation” and “skip”. Then, we demonstrate that the parsing performance of “skip” network can be noticeably improved by modifying the parameterization of skip layers. Furthermore, we introduce a “dense skip” architecture to retain a rich set of low-level information from the pre-trained CNN, which is essential to improve the low-level parsing performance. Meanwhile, we propose a CCN and place it on top of pre-trained CNNs, which is used to aggregate contexts for high-level feature maps so that robust high-level parsing can be achieved. We name our segmentation network enhanced fully convolutional network (EFCN) based on its significantly enhanced structure over FCN. Extensive experimental studies justify each contribution separately. Without bells and whistles, EFCN achieves state-of-the-arts on segmentation datasets of ADE20K, Pascal Context, SUN-RGBD, and Pascal VOC 2012.

ResTune: Resource Oriented Tuning Boosted by Meta-Learning for Cloud Databases

Abstract: Modern database management systems (DBMS) contain tens to hundreds of critical performance tuning knobs that determine the system runtime behaviors. To reduce the total cost of ownership, cloud database providers put in drastic effort to automatically optimize the resource utilization by tuning these knobs. There are two challenges. First, the tuning system should always abide by the service level agreement (SLA) while optimizing the resource utilization, which imposes strict constrains on the tuning process. Second, the tuning time should be reasonably acceptable since time-consuming tuning is not practical for production and online troubleshooting. In this paper, we design ResTune to automatically optimize the resource utilization without violating SLA constraints on the throughput and latency requirements. ResTune leverages the tuning experience from the history tasks and transfers the accumulated knowledge to accelerate the tuning process of the new tasks. The prior knowledge is represented from historical tuning tasks through an ensemble model. The model learns the similarity between the historical workloads and the target, which significantly reduces the tuning time by a meta-learning based approach. ResTune can efficiently handle different workloads and various hardware environments. We perform evaluations using benchmarks and real world workloads on different types of resources. The results show that, compared with the manually tuned configurations, ResTune reduces 65%, 87%, 39% of CPU utilization, I/O and memory on average, respectively. Compared with the state-of-the-art methods, ResTune finds better configurations with up to ~18x speedups.

Enhancing Social Media Analysis with Visual Data Analytics: A Deep Learning Approach

Abstract: This research methods article proposes a visual data analytics framework to enhance social media research using deep learning models. Drawing on the literature of information systems and marketing, complemented with data-driven methods, we propose a number of visual and textual content features including complexity, similarity, and consistency measures that can play important roles in the persuasiveness of social media content. We then employ state-of-the-art machine learning approaches such as deep learning and text mining to operationalize these new content features in a scalable and systematic manner. For the newly developed features, we validate them against human coders on Amazon Mechanical Turk. Furthermore, we conduct two case studies with a large social media dataset from Tumblr to show the effectiveness of the proposed content features. The first case study demonstrates that both theoretically motivated and data-driven features significantly improve the model’s power to predict the popularity of a post, and the second one highlights the relationships between content features and consumer evaluations of the corresponding posts. The proposed research framework illustrates how deep learning methods can enhance the analysis of unstructured visual and textual data for social media research.

Information Theoretic Subspace Clustering

Abstract: This paper addresses the problem of grouping the data points sampled from a union of multiple subspaces in the presence of outliers. Information theoretic objective functions are proposed to combine structured low-rank representations (LRRs) to capture the global structure of data and information theoretic measures to handle outliers. In theoretical part, we point out that group sparsity-induced measures ( $\ell _{2,1}$ -norm, $\ell _{\alpha }$ -norm, and correntropy) can be justified from the viewpoint of half-quadratic (HQ) optimization, which facilitates both convergence study and algorithmic development. In particular, a general formulation is accordingly proposed to unify HQ-based group sparsity methods into a common framework. In algorithmic part, we develop information theoretic subspace clustering methods via correntropy. With the help of Parzen window estimation, correntropy is used to handle either outliers under any distributions or sample-specific errors in data. Pairwise link constraints are further treated as a prior structure of LRRs. Based on the HQ framework, iterative algorithms are developed to solve the nonconvex information theoretic loss functions. Experimental results on three benchmark databases show that our methods can further improve the robustness of LRR subspace clustering and outperform other state-of-the-art subspace clustering methods.

Graph Convolution for Multimodal Information Extraction from Visually Rich Documents.

Abstract: Visually rich documents (VRDs) are ubiquitous in daily business and life. Examples are purchase receipts, insurance policy documents, custom declaration forms and so on. In VRDs, visual and layout information is critical for document understanding, and texts in such documents cannot be serialized into the one-dimensional sequence without losing information. Classic information extraction models such as BiLSTM-CRF typically operate on text sequences and do not incorporate visual features. In this paper, we introduce a graph convolution based model to combine textual and visual information presented in VRDs. Graph embeddings are trained to summarize the context of a text segment in the document, and further combined with text embeddings for entity extraction. Extensive experiments have been conducted to show that our method outperforms BiLSTM-CRF baselines by significant margins, on two real-world datasets. Additionally, ablation studies are also performed to evaluate the effectiveness of each component of our model.