Graph Neural Network (GNN) training and inference involve significant challenges of scalability with respect to both model sizes and number of layers, resulting in degradation of efficiency and accuracy for large and deep GNNs. We present an end-to-end solution that aims to address these challenges for efficient GNNs in resource constrained environments while avoiding the oversmoothing problem in deep GNNs. We introduce a quantization based approach for all stages of GNNs, from message passing in training to node classification, compressing the model and enabling efficient processing. The proposed GNN quantizer learns quantization ranges and reduces the model size with comparable accuracy even under low-bit quantization. To scale with the number of layers, we devise a message propagation mechanism in training that controls layer-wise changes of similarities between neighboring nodes. This objective is incorporated into a Lagrangian function with constraints and a differential multiplier method is utilized to iteratively find optimal embeddings. This mitigates oversmoothing and suppresses the quantization error to a bound. Significant improvements are demonstrated over state-of-the-art quantization methods and deep GNN approaches in both full-precision and quantized models. The proposed quantizer demonstrates superior performance in INT2 configurations across all stages of GNN, achieving a notable level of accuracy. In contrast, existing quantization approaches fail to generate satisfactory accuracy levels. Finally, the inference with INT2 and INT4 representations exhibits a speedup of 5.11 × and 4.70 × compared to full precision counterparts, respectively.

We present PPQ-trajectory, a spatio-temporal quantization based solution for querying large dynamic trajectory data. PPQ-trajectory includes a partition-wise predictive quantizer (PPQ) that generates an error-bounded codebook with autocorrelation and spatial proximity-based partitions. The codebook is indexed to run approximate and exact spatio-temporal queries over compressed trajectories. PPQ-trajectory includes a coordinate quadtree coding for the codebook with support for exact queries. An incremental temporal partition-based index is utilised to avoid full reconstruction of trajectories during queries. An extensive set of experimental results for spatio-temporal queries on real trajectory datasets is presented. PPQ-trajectory shows significant improvements over the alternatives with respect to several performance measures, including the accuracy of results when the summary is used directly to provide approximate query results, the spatial deviation with which spatio-temporal path queries can be answered when the summary is used as an index, and the time taken to construct the summary. Superior results on the quality of the summary and the compression ratio are also demonstrated.

Books, as a representative of lengthy documents, convey rich semantics. Traditional document modeling methods, such as bag-of-words models, have difficulty capturing such rich semantics when only considering term-frequency features. In order to explore term spatial distributions over a book, a tree-structured book representation is investigated in this paper. Moreover, an efficient learning framework, Tree2Vector, is introduced for mapping tree-structured book data into vectorial space. In particular, we present two types of locality reconstruction (LR) models: Euclidean-type and cosine-type, during the transformation process of tree structures into vectorial representations. The LR is used for modeling the reconstruction process, in which each parent node in a tree is supposed to be reconstructed by its child nodes. The prominent advantage of this Tree2Vector framework is that it solely utilizes the local information within a single book tree. In addition, extensive experimental results demonstrate that Tree2Vector is able to deliver comparable or better performance in comparison to methods that consider the information of all trees in a database globally. Experimental results also suggest that cosine-type LR consistently performs better than Euclidean-type LR in applications of book and author recommendations.

The tree structure is one of the most powerful structures for data organization. An efficient learning framework for transforming tree-structured data into vectorial representations is presented. First, in attempting to uncover the global discriminative information of child nodes hidden at the same level of all of the trees, a clustering technique can be adopted for allocating children into different clusters, which are used to formulate the components of a vector. Moreover, a locality-sensitive reconstruction method is introduced to model a process, in which each parent node is assumed to be reconstructed by its children. The resulting reconstruction coefficients are reversely transformed into complementary coefficients, which are utilized for locally weighting the components of the vector. A new vector is formulated by concatenating the original parent node vector and the learned vector from its children. This new vector for each parent node is inputted into the learning process of formulating vectorial representation at the upper level of the tree. This recursive process concludes when a vectorial representation is achieved for the entire tree. Our method is examined in two applications: book author recommendations and content-based image retrieval. Extensive experimental results demonstrate the effectiveness of the proposed method for transforming tree-structured data into vectors.

Dramatic growth of e-book sales revenue in recent years makes book recommendations essential to readers. Traditional bag-of-words models have difficulty of capturing the spatial information of terms over books. In this paper, a three-layer tree structure is used for representing each book. A framework, Tree2Vector, is designed for transforming tree-based book data into vectorial space. First, in order to characterize the global discriminative information of child nodes conveyed at the same level of all the trees, a clustering technique is used for assigning child nodes into different clusters, which are adopted for formulating the components of a vector. Furthermore, a locality reconstruction (LR) method is designed to model the reconstruction process, where each parent node is supposed to be reconstructed by its child nodes. The derived reconstruction coefficients are used for locally weighting the components of the vector. The process is repeated level-by-level until a vectorial representation is accomplished for a book tree. Our method is examined in content-based book recommendation. Experimental results exhibit the effectiveness of our framework.

In this paper, we present a new method for human object-level video advertising. A framework that aims to embed content-relevant ads within a video stream is investigated in this context. In particular, to support content-relevant advertising, we employ the discriminatively trained part based model to detect human objects in a video and then select the ads that are related to the detected human objects. For human clothing advertising, we design a deep Convolutional Neural Network (CNN) using face features to recognize human genders in a video stream. Human parts alignment is then implemented to extract human part features that are used for clothes retrieval. Our novel framework is examined in various types of videos. Experimental results demonstrate the effectiveness of the proposed method for human object-level video advertising.

Vehicle type recognition has many applications in video surveillance, urban traffic management and automatic driving. This paper presents a new vehicle type recognition method using feature encoding combined with Convolutional Neural Network (CNN). This method uses the CNN to learn the properties of the high-level image features. It is able to largely compensate the information loss if we use feature encoding solely. By contrast, to achieve satisfactory classification results, feature encoding algorithms do not need a large number of training samples. Thus, it can help CNN reduce the number of training samples. Therefore, we propose a hybrid algorithm by integrating method on vehicle type recognition in comparison to CNN, feature encoding algorithms and other competitive methods.

In this paper, we present a new framework for online video advertising by targeting clothes of principal actors. This framework aims to embed both character-relevant and content-relevant advertisements within a video stream. We identify the main actors automatically in a given video by using face clustering techniques. Specifically, we propose a new clustering algorithm based on face verification. Then we can find the main characters by counting the number of faces of each class. The video frames that include main characters are the best options to advertising. We segment the image patches of main characters from these video frames by object detection, and carry out different strategies for different sizes of images to match clothes ads. Experimental results demonstrate the effectiveness of our proposed method.