This study aims to address the challenges of financial price prediction in high-frequency trading (HFT) by introducing a novel continual learning framework based on factor predictors via graph neural networks. The model integrates multi-factor pricing theory with real-time market dynamics, effectively bypassing the limitations of conventional time series forecasting methods, which often lack financial theory guidance and ignore market correlations. We propose three heterogeneous tasks, including price gap regression, changepoint detection, and price moving average regression to trace the short-, intermediate-, and long-term trend factors present in the data. We also account for the cross-sectional correlations inherent in the financial market, where prices of different assets show strong dynamic correlations. To accurately capture these dynamic relationships, we resort to spatio-temporal graph neural network (STGNN) to enhance the predictive power of the model. Our model allows a continual learning strategy to simultaneously consider these tasks (factors). To tackle the catastrophic forgetting in continual learning while considering the heterogeneity of tasks, we propose to calculate parameter importance with mutual information between original observations and the extracted features. Empirical studies on the Chinese futures data and U.S. equity data demonstrate the superior performance of the proposed model compared to other state-of-the-art approaches.

It is challenging to predict futures prices with traditional econometric models as it necessitates a comprehensive consideration of both historical observations and correlations among various futures. Spatial-temporal graph neural networks (STGNNs) offer a promising approach for modeling such complex spatio-temporal data. Nevertheless, the direct application of STGNNs to high-frequency futures data remains a challenge, as traders must account for both short- and long-term characteristics when making decisions. To capture these distinct timeframes, we leverage additional label information by devising four heterogeneous tasks: price regression, price gap regression, price moving average regression, and change-point detection. To make full use of these labels, we train the model in a continual manner. Traditional continual GNNs define the gradient of losses as parameter importance to overcome the catastrophic forgetting (CF) issue, while this is unsuitable for our heterogeneous tasks with losses in distinct spaces. Therefore, we propose to calculate the parameter importance with mutual information between the original observations and the extracted features. The empirical results based on 49 varieties of commodity futures demonstrate that our model achieves superior performance compared to the leading approaches, highlighting the effectiveness of our approach in modeling the intricate dynamics of the futures market.

Autism spectrum disorder (ASD) is a complex neurodevelopmental disorder that affects socialization and is characterized by abnormal, restricted, or repetitive language behaviors. Symptoms typically start to appear around the age of 2, making early diagnosis essential for treatment. One standardized screening method is an autism-specific interview with children's parents. However, this diagnostic process requires highly experienced physicians, making questionnaire-based screening less effective. Recently, imaging-based diagnosis has emerged as a more objective option. In this paper, we propose a graph neural network-based model for ASD diagnosis using Diffusion Tensor Imaging (DTI) and functional Magnetic Resonance Imaging (fMRI) data. We first calculate the correlations of 90 brain regions based on the automated anatomical labeling (AAL) template using brain imaging data of DTI and fMRI. This enables the construction of a comprehensive network map that delineates the interconnections among various brain regions. Subsequently, we propose to utilize a graph neural network for the purpose of diagnosing ASD, wherein the graph derived from DTI serves as the adjacency matrix, while the map of the fMRI is utilized as the node features. To improve the performance of diagnosis, we introduce a regularization of maximum inter-class graph distance and minimum intra-class graph distance, in addition to graph classification. We then calculate the correlation matrix between functional areas based on the obtained 90 implicit features corresponding to the nodes of functional areas and their 90 eigenvalues. We also perform hypothesis tests on the 90 eigenvalues corresponding to ASD negative and positive groups in turn to discover the pathogenic functional areas by comparing the eigenvalue distributions between the two groups. Our experiments on 138 real-world samples demonstrate the superior performance of our proposed model for diagnosis.

Although self-supervised learning (SSL) has been successfully applied to graph data using graph neural networks (GNNs), most of the existing methods only consider undirected graphs where relationships among connected nodes are two-way symmetric (i.e., information can be passed back and forth between two connected nodes). However, there is a vast amount of applications where the information flow is asymmetric, leading to directed graphs where information can only be passed along one direction. For example, a directed edge indicates that the information can only be conveyed forwardly from the start node to the end node, but not backwardly. To accommodate such an asymmetric structure of directed graphs, we propose a simple yet remarkably effective SSL framework for directed graph analysis to incorporate such one-way information passing. We define an incoming embedding and an outgoing embedding for each node to model its schemes of sending and receiving features respectively. We propose an auxiliary SSL task to predict the existence of the directed edges with the incoming and outgoing embeddings of nodes. The auxiliary SSL task is jointly trained with a downstream primary task that updates nodes’ incoming features and outgoing features in accordance with labels. Extensive experiments on multiple real-world directed graph datasets demonstrate outstanding performances of the proposed self-supervised GNNs in both node-level and graph-level tasks.

Semisupervised learning (SSL) has been extensively studied in related literature. Despite its success, many existing learning algorithms for semisupervised problems require specific distributional assumptions, such as "cluster assumption" and "low-density assumption," and thus, it is often hard to verify them in practice. We are interested in quantifying the effect of SSL based on kernel methods under a misspecified setting. The misspecified setting means that the target function is not contained in a hypothesis space under which some specific learning algorithm works. Practically, this assumption is mild and standard for various kernel-based approaches. Under this misspecified setting, this article makes an attempt to provide a theoretical justification on when and how the unlabeled data can be exploited to improve inference of a learning task. Our theoretical justification is indicated from the viewpoint of the asymptotic variance of our proposed two-step estimation. It is shown that the proposed pointwise nonparametric estimator has a smaller asymptotic variance than the supervised estimator using the labeled data alone. Several simulated experiments are implemented to support our theoretical results.

We propose to learn distributed sentence representation using the text's visual features as input.Different from the existing methods that render the words (or characters) of a sentence into images separately, we fold these images into a 3-dimensional sentence tensor.Then, multiple 3dimensional convolutions with different lengths (the third dimension) are applied to the sentence tensor, which would act as bi-gram, tri-gram, quad-gram, and even five-gram detectors jointly.Similar to the Bi-LSTMs, these n-gram detectors learn both forward and backward distributional semantic knowledge from the sentence tensor.The proposed model uses bi-directional convolutions to learn text embedding according to the semantic order of words.The feature maps from the two directions are concatenated for final sentence embedding learning.Our model involves only a single layer of convolution which makes it easy and fast to train.We evaluate the sentence embeddings on several downstream natural language processing (NLP) tasks, which demonstrate surprisingly excellent performance of the proposed model.

By setting a typeface, each character of the Chinese text can be converted to a glyph pixel matrix. We propose to conduct text classification with such glyph features using bi-directional convolution. Although the pixel embedding can be applied to all languages, it is much more convenient to be used to represent Chinese scripts due to the square shape of Chinese characters. We extract both the forward and backward n-gram features of the text via bi-directional convolutional operations and then concatenate them. A subsequent 1-dimensional max-over-time pooling is applied to the bi-directional feature maps, and then three fully connected layers are used for conducting text classification. The proposed model has a light-weight architecture that only contains a single-layer convolutional neural network. Experiments on several Chinese text classification datasets demonstrate surprisingly excellent results for the training speed and superior performance of the proposed model in comparison with traditional methods.

Link prediction is a fundamental problem in network modeling. A family of link prediction approaches is to treat network data as an exchangeable array whose entries can be explained by random functions (e.g., block models and Gaussian processes) over latent node factors. Despite their powerful ability in modeling missing links, these models tend to have a large computational complexity and thus are hard to deal with large networks. To address this problem, we develop a novel variational random function model by defining latent Gaussian processes on exchangeable arrays. This model not only inherits the ability of Gaussian process to describe the nonlinear interactions between nodes, but also enjoys significant reduction on computational complexity. To further make the model scalable to large network data, we develop an efficient key-value-free strategy under the map-reduce framework to tremendously reduce the inference time. Experimental results on large network data have demonstrated both the efficacy and efficiency of the proposed method over state-of-the-arts methods in network modeling.

Standard recommender systems usually rely only on past user ratings as well as optional profiles of customers and products. In e-commerce settings, however, a more complete understanding of the corresponding bi-directional impact between the demands of customers and the supply capabilities of providers can be the key to success. This motivates us to design a recommendation model that explicitly reflects the supply and demand chains. We propose a Multi-relational Coupled Tensor and Matrix Factorization model, which jointly models user ratings as well as supply chain relationships for product recommendation. In addition, our model can predict the links between suppliers and manufacturers. We design an algorithm based on the Alternating Direction Method of Multipliers (ADMM) technique. Experiments on real-world datasets find that the proposed model outperforms traditional methods.

We present a matrix completion based multi-label learning model to handle the Gene functional annotation problem in this article. We consider the labels of Gene expression data as missing values of a construction matrix composed of expression data and label matrices. By assuming that the construction matrix as low rank and manifold structure, we can recover all the missing labels with minimization of its rank under constraints of data observed. The theories behind the low rank and manifold assumptions are the data correlation and similar data points sharing similar labels. Besides, the constructed matrix contains heterogeneous entries (continuous Gene expression data and binary labels), which existing works failed to model. To seal the gap between labels and expression data during prediction, we regularize our model with the maximum likelihood of unknown labels. A modified fixed-point continuation method is proposed to optimize the resulting nuclear norm minimization problem. The promising results of the proposed method on functional label predicting of Yeast gene microarray data have been shown in experiments.

We consider a different setting from regular multitask learning, where data from different tasks share no common instances and no common feature dictionary, while the features can be semantically correlated and all tasks share the same class space. For example, in the two tasks of identifying terrorism information from English news and Arabic news respectively, one associated dataset could be news from Cable News Network (CNN), and the other be news crawled from websites of Arabic countries. Intuitively, these two tasks could help each other, although they share no common feature space. This new setting has brought obstacles to traditional multi-task learning algorithms and multi-view learning algorithms. We argue that these different data sources can be co-trained together by exploring the latent semantics among them. To this end, we propose a new graphical model based on sparse Gaussian Conditional Random Fields (GCRF) and Hilbert-Schmidt Independence Criterion (HSIC). In additional to output the prediction accuracy for each single task, it can also model (1) the dependency between the latent feature spaces of different tasks, (2) the dependency of the category spaces, and (3) the dependency between the latent feature space and the category space in each task. To make the model inference effective, we have provided an efficient variational EM algorithm. Experiments on both synthetic data sets and real-world data sets have indicated the feasibility and effectiveness of the proposed framework.

In social network analysis, we often need to predict new links, given some available evidence. This may, for instance, enable us to study user behavior and infer likely new interactions in the near future. Recently, a family of algorithms based on exchangeable graphs has proven effective for link prediction. The network is modeled as an exchangeable array, whose entries can flexibly be traced back to random function priors (e.g., block models, Gaussian Processes). Unfortunately, the burdensome computational complexity of these methods inhibit their application to even just moderate-scale networks. In this paper, we present a novel online training algorithm based on local Gaussian processes on subgraphs, which successfully overcomes this challenge. Moreover, we address the sparsity problem of links in social networks by presenting an improved algorithm based on network formation games. The network formation games we design also shed light on the ambiguity of missing links - not observed vs. non-existing. We evaluate our method against state-of-the-art algorithms on real-world datasets, demonstrating both the effectiveness and the efficiency of our method.

Link prediction in multi-relational social networks has attracted much attention. For instance, we may care the chance of two users being friends based on their contacts of other patterns, e.g., SMS and phone calls. In previous work, matrix factorization models are typically applied in single-relational networks; however, two challenges arise to extend it into multi-relational networks. First, the interaction of different relation types is hard to be captured. The second is the cold start problem, as the prediction of new entities in multi-relational networks becomes even more challenging. In this article we propose a novel method called Hierarchical Probabilistic Matrix Factorization with Network Topology (HPMFNT). Our model exploits the network topology by extending the Katz index into multi-relational settings, which could efficiently model the multidimensional interplay via the auxiliary information from other relationships. We also utilize the extended Katz index along with entitiy attributes to solve the cold-start problem. Experiments on two real world datasets have shown that our model outperforms the state-of-the-art with a significant margin.

The development of the smartphones with various sensors, and powerful capabilities (computing, storage, and communication), motivates a popular computing and sensing paradigm, crowdsensing. In general, in crowdsensing, the smart-phones sense and collect the sensory data from a large number of smartphone users, for distinguishing the uncertain objects. However, some existing solutions for crowdsensing usually prefer to utilize only one or few features to distinguish the uncertain objects. In this paper, due to the limitation of less features, we propose to utilize multiple features to distinguish the uncertain objects for crowdsensing. For distinguishing uncertain objects with multiple features, we propose to utilize KL divergence based clustering. Moreover, we introduce two other mutated forms, the symmetry KL divergence and Jensen-Shannon KL divergence, to improve our algorithm. We evaluate our proposed schemes with real data of multiple features, which are collected by the smartphones with the sensors.

Uncertain data are inherent in mobile crowd sensing applications, and the objects that they correspond to are usually vaguely specified. In order to improve performance, we often increase the number of features. However, the more features are used, the more redundancy and cost are involved correspondingly. Therefore, the number of features we selected for a specified application is a tradeoffs between the accuracy and the cost. In this paper, we model such tradeoffs between accuracy and cost as an optimization problem. Moreover, for investigating this problem, we propose to model the sensing with multiple features under a hypercube structure. In our scheme, each feature of uncertain objects is represented as a component of the vertex's coordinate in hypercube. At the same time, we prefer to define the edges between vertices with relative entropy rather than Euclidean distance. Because the former one could accurately measures the difference between two probability distributions of data. We evaluate our proposed schemes with real data of a crowd sensing recognition case, which are collected by smartphones with sensors.