Deep sequence networks such as multi-head self-attention networks provide a promising way to extract effective representations from raw sequence data in an end-to-end fashion and have shown great success in various domains such as natural language processing, computer vision, $etc$. However, in domains such as financial risk management and anti-fraud where expert-derived features are heavily relied on, deep sequence models struggle to dominate the game.In this paper, we introduce a simple framework called symbolic testing to verify the learnability of certain expert-derived features over sequence data. A systematic investigation over simulated data reveals the fact that the self-attention architecture fails to learn some standard symbolic expressions like the count distinct operation. To overcome this deficiency, we propose a novel architecture named SHORING, which contains two components:event network andsequence network. Theevent network efficiently learns arbitrary high-orderevent-level conditional embeddings via a reparameterization trick while thesequence network integrates domain-specific aggregations into the sequence-level representation, thereby providing richer inductive biases compare to standard sequence architectures like self-attention. We conduct comprehensive experiments and ablation studies on synthetic datasets that mimic sequence data commonly seen in anti-fraud domain and three real-world datasets. The results show that SHORING learns commonly used symbolic features well, and experimentally outperforms the state-of-the-art methods by a significant margin over real-world online transaction datasets. The symbolic testing framework and SHORING have been applied in anti-fraud model development at Alipay and improved performance of models for real-time fraud-detection.

Dynamic graphs such as the user-item interactions graphs and financial transaction networks are ubiquitous nowadays. While numerous representation learning methods for static graphs have been proposed, the study of dynamic graphs is still in its infancy. A main challenge of modeling dynamic graphs is how to effectively encode temporal and structural information into nonlinear and compact dynamic embeddings. To achieve this, we propose a principled graph-neural-based approach to learn continuous-time dynamic embeddings. We first define a temporal dependency interaction graph(TDIG) that is induced from sequences of interaction data. Based on the topology of this TDIG, we develop a dynamic message passing neural network named TDIG-MPNN, which can capture the fine-grained global and local information on TDIG. In addition, to enhance the quality of continuous-time dynamic embeddings, a novel selection mechanism comprised of two successive steps, i.e., co-attention and gating, is applied before the above TDIG-MPNN layer to adjust the importance of the nodes by considering high-order correlation between interactive nodes' k-depth neighbors on TDIG. Finally, we cast our learning problem in the framework of temporal point processes (TPPs) where we use TDIG-MPNN to design a neural intensity function for the dynamic interaction processes. Our model achieves superior performance over alternatives on temporal interaction prediction (including tranductive and inductive tasks) on multiple datasets.

We propose a modeling framework for event data and aim to answer questions such as \emph{when} and \emph{why} the next event would happen. Our proposed model excels in small data regime with the ability to incorporate domain knowledge in terms of logic rules. We model the dynamics of the event starts and ends via intensity function with the structures informed by a set of first-order temporal logic rules. Using the softened representation of temporal relations, and a weighted combination of logic rules, our probabilistic model can deal with uncertainty in events. Furthermore, many well-known point processes (e.g., Hawkes process, self-correcting point process) can be interpreted as special cases of our model given simple temporal logic rules. Our model, therefore, riches the family of point processes. We derive a maximum likelihood estimation procedure for our model and show that it can lead to accurate predictions when data are sparse and domain knowledge is critical.

A novel sports genre categorization algorithm based on representative shot extraction and geometry visual phrase(GVP) is presented in this paper. Performance of sports classification can be observably improved by generating reduced image set containing representative information and encoding spatial information into bag-of-words (BOW) model. Firstly, Shots containing significant information of videos are chosen by key-frame clustering. Secondly, GVP are searched by the co-occurrence of visual words in a spatial layout based on scale invariant feature transform (SIFT). Then visual words and GVP are concatenated to form enhanced histograms before SVM based classifying procedure. Compared with most existing methods, our algorithm is domain knowledge free as well as fully automatic and thus provides better extensibility. Experiments on a database of 10 sport genres with over 10257 minutes of videos from different sources achieved an average accuracy of 87.3%, which validates the robustness of our proposed algorithm over large-scale database.

A TV program segmentation algorithm is presented by the fusion of the multi-modal information in the large-scale videos. As "Inter-Programs" are generally inserted into the TV videos repeatedly, the macro structures of the videos can be effectively and automatically generated by identifying the video-audio features of the special sequences. The Electronic Program Guide (EPG) is used to organize the structures into the programs. Three sections are included in the algorithm, namely, the video-based non-supervised duplicate sequence detection, the audio-based special clip retrieval and the EPG-based 24-hour program segmentation. The algorithm has been tested in 60-day different-type TV videos. The F-measures of the multi-modal fusion and video-based duplicated sequence detection achieve the rates of over 98% and 96% respectively. These results show that the proposed method is highly efficient and effective for the TV Program segmentation.