-
Chapter and Conference Paper
Incorporating Ranking Context for End-to-End BERT Re-ranking
Ranking context has been shown crucial for the performance of learning to rank. Its use for the BERT-based re-rankers, however, has not been fully explored. In this work, an end-to-end BERT-based ranking model...
-
Chapter and Conference Paper
Graph Attention Collaborative Similarity Embedding for Recommender System
We present Graph Attention Collaborative Similarity Embedding (GACSE), a new recommendation framework that exploits collaborative information in the user-item bipartite graph for representation learning. Our f...
-
Chapter and Conference Paper
Toward the New Item Problem: Context-Enhanced Event Recommendation in Event-Based Social Networks
Increasing popularity of event-based social networks (EBSNs) calls for the developments in event recommendation techniques. However, events are uniquely different from conventional recommended items because ev...
-
Chapter and Conference Paper
Content Based Retrieval for Lunar Exploration Image Databases
Being a novel research aspect following the recent new round of lunar explorations, content-based lunar image retrieval provides a convenient and efficient way for accessing relevant lunar remote sensing image...
-
Chapter and Conference Paper
On Efficient k-Skyband Query Processing over Incomplete Data
The Skyline query and its variants have been extensively explored in the literature. Existing approaches, except one, assume that all dimensions are available for all data items. However, many practical applicati...
-
Chapter and Conference Paper
The Concept of eTextbooks in K-12 Classes from the Perspective of Its Stakeholders
With the emergence of eTextbooks initiatives on the rise, it is promising that eTextbooks support significant opportunities for improving the educational practices. However, there are both positive and negativ...
-
Chapter and Conference Paper
Enhancing Utility and Privacy-Safety via Semi-homogenous Generalization
The existing solutions to privacy preserving publication can be classified into the homogenous and non-homogenous generalization. The generalization of data increases the uncertainty of attribute values, and l...
-
Chapter and Conference Paper
All-Visible-k-Nearest-Neighbor Queries
The All-k-Nearest-Neighbor (AkNN) operation is common in many applications such as GIS and data analysis/mining. In this paper, for the first time, we study a novel variant of AkNN queries, namely All-Visible-k-N...
-
Chapter and Conference Paper
Acolyte: An In-Memory Social Network Query System
WISE 2012 Challenge provides a data set crawled from Sina Weibo, which consists of hundreds of millions of anonymized following relationships and microblogs. In the performance track, 19 typical queries on the...
-
Chapter and Conference Paper
On Efficient Reverse k-Skyband Query Processing
This paper, for the first time, addresses the problem of efficient reverse k-skyband (RkSB) query processing. Given a set P of multi-dimensional points and a query point q, an RkSB query returns all the points in...
-
Chapter and Conference Paper
Top-Down SLCA Computation Based on List Partition
In this paper, we focus on efficient processing of a given XML keyword query based on SLCA semantics. We propose an efficient algorithm that processes all nodes in the set of inverted Dewey label lists in a top-d...
-
Chapter and Conference Paper
Fast Result Enumeration for Keyword Queries on XML Data
In this paper, we focus on efficient construction of tightest matched subtree (TMSubtree) results for keyword queries on XML data based on SLCA semantics, where “matched” means that all nodes in a returned subtre...
-
Chapter and Conference Paper
Aggregate Farthest-Neighbor Queries over Spatial Data
In this paper, we study a new type of spatial query, namely aggregate k farthest neighbor (AkFN) search. Given a data point set P, a query point set Q, an AkFN query returns k points in P with the largest aggrega...
-
Chapter and Conference Paper
Listen! Somebody Is Walking towards Your Car (Introducing the Awareness-3D Sound System into the Driver to Increase the Pedestrian’s Safety)
Car accident statistics indicate that the pedestrians are the majority of the road traffic victims due to drivers’ lack of adequate visibility on the road. In this paper, the effects of human natural sounds in...
-
Chapter and Conference Paper
\(\textrm{B}^s\) -tree: A Self-tuning Index of Moving Objects
Self-tuning database is a general paradigm for the future development of database systems. However, in moving object database, a vibrant and dynamic research area of the database community, the need for self-t...
-
Chapter and Conference Paper
Transfer Regression Model for Indoor 3D Location Estimation
Wi-Fi based indoor 3D localization is becoming increasingly prevalent in today’s pervasive computing applications. However, traditional methods can not provide accurate predicting result with sparse training d...
-
Chapter and Conference Paper
Distributed Cache Indexing for Efficient Subspace Skyline Computation in P2P Networks
Skyline queries play an important role in applications such as multi-criteria decision making and user preference systems. Recently, more attention has been paid to the problem of efficient skyline computation...
-
Chapter and Conference Paper
Update Migration: An Efficient B+ Tree for Flash Storage
More and more evidence indicates that flash storage is a potential substitute for magnetic disk in the foreseeable future. Due to the high-speed random reads, flash storage could improve the performance of DBM...
-
Chapter and Conference Paper
Attribute Outlier Detection over Data Streams
Outlier detection is widely used in many data stream application, such as network intrusion detection, fraud detection, etc. However, most existing algorithms focused on detecting class outliers and there is l...
-
Chapter and Conference Paper
iDISQUE: Tuning High-Dimensional Similarity Queries in DHT Networks
In this paper, we propose a fully decentralized framework called iDISQUE to support tunable approximate similarity query of high dimensional data in DHT networks. The iDISQUE framework utilizes a distributed i...