Search

Tree-based models and deep neural networks are two schools of effective classification methods in machine learning. While tree-based models are robust irrespective of data domain, deep neural networks have advantages in handling high-dimensional data. Adding a differentiable neural decision forest to the neural network can generally help exploit the benefits of both models. Therefore, traditional decision trees diverge into a bagging version (i.e., random forest) and a boosting version (i.e., gradient boost decision tree). In this work, we aim to harness the advantages of both bagging and boosting by applying gradient boost to a neural decision forest. We propose a gradient boost that can learn the residual using a neural decision forest, considering the residual as a part of the final prediction. Besides, we design a structure for learning the parameters of neural decision forest and gradient boost module in contiguous steps, which is extendable to incorporate multiple gradient-boosting modules in an end-to-end manner. Our extensive experiments on several public datasets demonstrate the competitive performance and efficiency of our model against a series of baseline methods in solving various machine learning tasks.

Temporal relational data, perhaps the most commonly used data type in industrial machine learning applications, needs labor-intensive feature engineering and data analyzing for giving precise model predictions. An automatic machine learning framework is needed to ease the manual efforts in fine-tuning the models so that the experts can focus more on other problems that really need humans' engagement such as problem definition, deployment, and business services. However, there are three main challenges for building automatic solutions for temporal relational data: 1) how to effectively and automatically mining useful information from the multiple tables and the relations from them? 2) how to be self-adjustable to control the time and memory consumption within a certain budget? and 3) how to give generic solutions to a wide range of tasks? In this work, we propose our solution that successfully addresses the above issues in an end-to-end automatic way. The proposed framework, AutoSmart, is the winning solution to the KDD Cup 2019 of the AutoML Track, which is one of the largest AutoML competition to date (860 teams with around 4,955 submissions). The framework includes automatic data processing, table merging, feature engineering, and model tuning, with a time\&memory controller for efficiently and automatically formulating the models. The proposed framework outperforms the baseline solution significantly on several datasets in various domains., Accepted in the ADS track at the SIGKDD 2021 conference

Ratings are an essential criterion for evaluating the quality of movies and a critical indicator of whether a customer would watch a movie. Therefore, an important related research challenge is to predict the rating of a movie before it is released in cinema or even before it is produced. Many existing approaches fail to address this challenge because they predict movie ratings based on post-production factors such as review comments from social media. Consequently, they are generally inapplicable until a movie has been released for a certain period of time when a sufficient number of review comments have become available. In this paper, we propose a regression model based on generative convolutional neural networks for movie rating prediction. Instead of post-production factors widely used by previous work, this model learns from movies’ intrinsic pillars such as genres, budget, cast, director and plot information, which are obtainable before the production of movies. In particular, the model explores the correlations between the rating of a movie and its intrinsic attributes to predict its rating. The results can serve as a reference for investors and movie studios to determine an optimal portfolio for movie production and a guidance to the interested users to choose the movie to watch. Extensive experiments on a real dataset are benchmarked against a set of baselines and state of the art approaches. The results demonstrate the effectiveness of our approach. The proposed model is also general to be extended to handle other prediction tasks.

Objective: Epilepsy is a chronic neurological disorder characterized by the occurrence of spontaneous seizures, which affects about one percent of the world's population. Most of the current seizure detection approaches strongly rely on patient history records and thus fail in the patient-independent situation of detecting the new patients. To overcome such limitation, we propose a robust and explainable epileptic seizure detection model that effectively learns from seizure states while eliminates the inter-patient noises. Methods: A complex deep neural network model is proposed to learn the pure seizure-specific representation from the raw non-invasive electroencephalography (EEG) signals through adversarial training. Furthermore, to enhance the explainability, we develop an attention mechanism to automatically learn the importance of each EEG channels in the seizure diagnosis procedure. Results: The proposed approach is evaluated over the Temple University Hospital EEG (TUH EEG) database. The experimental results illustrate that our model outperforms the competitive state-of-the-art baselines with low latency. Moreover, the designed attention mechanism is demonstrated ables to provide fine-grained information for pathological analysis. Conclusion and significance: We propose an effective and efficient patient-independent diagnosis approach of epileptic seizure based on raw EEG signals without manually feature engineering, which is a step toward the development of large-scale deployment for real-life use., Accepted by the IEEE Journal of Biomedical and Health Informatics (J-BHI)

© 2019 IEEE. The prevalence of online social media facilitates massive knowledge acquisition and sharing throughout the Web. Meanwhile, it inevitably poses the risk of generating and disseminating false information by both benign and malicious users. Despite there has been considerable research on false information detection from both the opinion-based and fact-based perspectives, they mostly focus on tailored solutions for a particular domain and carry out limited work on leveraging multi-faceted clues such as textual cues, behavioral trails, and relational connection. We propose a novel dual-stream attentive random forest that is capable of selecting clues of discriminative information from individuals, collective information (e.g., texts), and correlations of entities (e.g., social interactions) adaptively. In particular, we use an interpretive attention model for learning textual contents. The model treats the important and unimportant content differently when constructing the textual representation and employs a multilayer perceptron to capture the hidden complex relationships among features of side information. We further propose a unified framework for leveraging the above clues, where we use attentive forests to provide probabilistic distribution as predictions over the two learned representations, which are then leveraged to make a better estimation. We conduct extensive experiments on three real-world benchmark datasets for fake news and fake review detection. The results show our approach outperforms multiple baselines in the accuracy of detecting false information.

© Springer Nature Switzerland AG 2019. Clickbait is a type of web content advertisements designed to entice readers into clicking accompanying links. Usually, such links will lead to articles that are either misleading or non-informative, making the detection of clickbait essential for our daily lives. Automated clickbait detection is a relatively new research topic. Most recent work handles the clickbait detection problem with deep learning approaches to extract features from the meta-data of content. However, little attention has been paid to the relationship between the misleading titles and the target content, which we found to be an important clue for enhancing clickbait detection. In this work, we propose a deep similarity-aware attentive model to capture and represent such similarities with better expressiveness. In particular, we present the ways of either using similarity only or integrating it with other available quality features for the clickbait detection. We evaluate our model on two benchmark datasets, and the experimental results demonstrate the effectiveness of our approach by outperforming a series of competitive state-of-the-arts and baseline methods.

Community question answering (CQA) represents the type of Web applications where people can exchange knowledge via asking and answering questions. One significant challenge of most real-world CQA systems is the lack of effective matching between questions and the potential good answerers, which adversely affects the efficient knowledge acquisition and circulation. On the one hand, a requester might experience many low-quality answers without receiving a quality response in a brief time, on the other hand, an answerer might face numerous new questions without being able to identify their questions of interest quickly. Under this situation, expert recommendation emerges as a promising technique to address the above issues. Instead of passively waiting for users to browse and find their questions of interest, an expert recommendation method raises the attention of users to the appropriate questions actively and promptly. The past few years have witnessed considerable efforts that address the expert recommendation problem from different perspectives. These methods all have their issues that need to be resolved before the advantages of expert recommendation can be fully embraced. In this survey, we first present an overview of the research efforts and state-of-the-art techniques for the expert recommendation in CQA. We next summarize and compare the existing methods concerning their advantages and shortcomings, followed by discussing the open issues and future research directions., 29 pages, Journal of Computer Science and Technology, January 2018

Modeling user-item interaction patterns is an important task for personalized recommendations. Many recommender systems are based on the assumption that there exists a linear relationship between users and items while neglecting the intricacy and non-linearity of real-life historical interactions. In this paper, we propose a neural network based recommendation model (NeuRec) that untangles the complexity of user-item interactions and establishes an integrated network to combine non-linear transformation with latent factors. We further design two variants of NeuRec: user-based NeuRec and item-based NeuRec, by concentrating on different aspects of the interaction matrix. Extensive experiments on four real-world datasets demonstrated their superior performances on personalized ranking task., Accepted at IJCAI 2018