26 May 2023 in Proceedings of the ACM on Management of Data
Learned indexes have been proposed to replace classic index structures like B-Tree with machine learning (ML) models. They require to replace both the indexes and query processing algorithms currently deployed by the databases, and such a radical departure is likely to encounter challenges and obstacles. In contrast, we propose a fundamentally different way of using ML techniques to build a better R-Tree without the need to change the structure or query processing algorithms of traditional R-Tree. Specifically, we develop reinforcement learning (RL) based models to decide how to choose a subtree for insertion and how to split a node when building and updating an R-Tree, instead of relying on hand-crafted heuristic rules currently used by the R-Tree and its variants. Experiments on real and synthetic datasets with up to more than 100 million spatial objects show that our RL based index outperforms the R-Tree and its variants in terms of query processing time.
17 April 2023 in IEEE Transactions on Knowledge and Data Engineering
The wide spread of rumors inflicts damages on social media platforms. Detecting rumors has become an emerging problem concerning the public and government. A crucial problem for rumors detection on social media is the lack of reliably pre-annotated dataset to train classification models. To solve this problem, we propose an unsupervised model that detects rumors by measuring how well the tweets follow the normal patterns. However, the problem is challenging in how to automatically discover the normal patterns of tweets. To tackle the challenge, we first propose a novel tree variational autoencoder model that reconstructs the sentiment labels along the propagation tree of a factual tweet. Then we propose a cross-alignment method to align the multiple modalities, i.e. tree structure and propagation features, and output the final prediction results. We conduct extensive experiments on a real-world dataset collected from Weibo. The experiments show that the proposed method significantly outperforms the state-of-the-art unsupervised methods and adapts better to the concept drift than state-of-the-art supervised methods.
26 May 2023 in Proceedings of the ACM on Management of Data
Geo-textual objects with both geographical location and textual description are gaining in prevalence. Over the past decades, substantial research has been conducted on spatial keyword queries, which integrate location into keyword-based querying of geo-textual content. However, existing proposals mostly focus on efficiency for processing spatial keyword queries, and little effort was made to address the effectiveness perspectives. In this work, using two datasets with ground truth query results, we evaluate the effectiveness of standard spatial keyword queries. Our evaluation results show that the TkQ query that ranks objects by a weighted combination of spatial proximity and text relevance is the most effective. Motivated by the finding, we propose a Deep relevance with Weight learning (DrW) model to further improve the effectiveness of the retrieval ranking. DrW is featured with two novel ideas: First, we propose a neural network architecture to learn the text relevance matching over the local interaction between the query and geo-textual objects. Second, we find that a query-dependent weight to balance text relevance and spatial proximity in ranking can improve effectiveness, and we develop a learning-based method to learn the query-dependent weight. Experimental results reveal that our model outperforms state-of-the-art methods on effectiveness, with improvements up to 32.15%, 32.34%, and 33.00% in terms of NDCG@3, NDCG@5, and MRR.
30 April 2024 in Information Sciences
8 May 2019 in IEEE Transactions on Knowledge and Data Engineering
With the proliferation of mobile devices and location-based services, continuous generation of massive volume of streaming spatial objects (i.e., geo-tagged data) opens up new opportunities to address real-world problems by analyzing them. In this paper, we present a novel continuous bursty region detection (SURGE) problem that aims to continuously detect a bursty region of a given size in a specified geographical area from a stream of spatial objects. Specifically, a bursty region shows maximum spike in the number of spatial objects in a given time window. The SURGE problem is useful in addressing several real-world challenges such as surge pricing problem in online transportation and disease outbreak detection. To solve the problem, we propose an exact solution and two approximate solutions, and the approximation ratio is $\frac{1-\alpha}{4}$ in terms of the burst score, where $\alpha$ is a parameter to control the burst score. We further extend these solutions to support detection of top-k bursty regions. Extensive experiments with real-world data are conducted to demonstrate the efficiency and effectiveness of our solutions.
30 September 2024 in Proceedings of the ACM on Management of Data
With the increasing availability of trajectory data, it is important to have good indexes to facilitate query processing. In this work, we propose BT-Tree, which is built through a recursive bi-partitioning approach, for the processing of range and KNN queries for past trajectory data. We first propose a cost function based method (CFBM) to build the BT-Tree. Specifically, we design a novel cost function, which incorporates the characteristics of both the data and historical query workload, to decide how to partition a BT-Tree node. Then we propose a reinforcement learning (RL) based method to address CFBM's limitations, such as making locally optimal decisions that may lead to global suboptimality. Experiments on three real datasets with up to 800 million data points show that the CFBM generally outperforms the baselines in terms of query processing time and the RL based method consistently outperforms the baselines and has more significant advantages on larger datasets.