Walk-Steered Convolution (WSC)
Graph classification is a fundamental but challenging problem due to the non-Euclidean property of graph. In this work, we jointly leverage the powerful representation ability of random walk and the essential success of standard convolutional network work (CNN), to propose a random walk based convolutional network, called walk-steered convolution (WSC). Different from those existing graph CNNs with deterministic neighbor searching, we randomly sample multi-scale walk fields by using random walk, which is more flexible to the scalability of graph. To encode each-scale walk field consisting of several walk paths, specifically, we characterize the directions of walk field by multiple Gaussian models so as to better analogize the standard CNNs on images. Each Gaussian implicitly defines a directions and all of them properly encode the spatial layout of walks after the gradient projecting to the space of Gaussian parameters. Further, a graph coarsening layer using dynamical clustering is stacked upon the Gaussian encoding to capture high-level semantics of graph. Comprehensive evaluations on several public datasets well demonstrate the superiority of our proposed graph learning method over other state-of-the-arts for graph classification. …

Tree Based Context Causal Rule Discovery (TCC)
With the increasing need of personalised decision making, such as personalised medicine and online recommendations, a growing attention has been paid to the discovery of the context and heterogeneity of causal relationships. Most existing methods, however, assume a known cause (e.g. a new drug) and focus on identifying from data the contexts of heterogeneous effects of the cause (e.g. patient groups with different responses to the new drug). There is no approach to efficiently detecting directly from observational data context specific causal relationships, i.e. discovering the causes and their contexts simultaneously. In this paper, by taking the advantages of highly efficient decision tree induction and the well established causal inference framework, we propose the Tree based Context Causal rule discovery (TCC) method, for efficient exploration of context specific causal relationships from data. Experiments with both synthetic and real world data sets show that TCC can effectively discover context specific causal rules from the data. …

Conformable Fractional Grey Model (CFGM)
The fractional order grey models (FGM) have appealed considerable interest of research in recent years due to its higher effectiveness and flexibility than the conventional grey models and other prediction models. However, the definitions of the fractional order accumulation (FOA) and difference (FOD) is computationally complex, which leads to difficulties for the theoretical analysis and applications. In this paper, the new definition of the FOA are proposed based on the definitions of Conformable Fractional Derivative, which is called the Conformable Fractional Accumulation (CFA), along with its inverse operation, the Conformable Fractional Difference (CFD). Then the new Conformable Fractional Grey Model (CFGM) based on CFA and CFD is introduced with detailed modelling procedures. The feasibility and simplicity and the CFGM are shown in the numerical example. And the at last the comprehensive real-world case studies of natural gas production forecasting in 11 countries are presented, and results show that the CFGM is much more effective than the existing FGM model in the 165 subcases. …

Bayesian Task-Adaptive Meta-Learning (Bayesian-TAML)
While tasks could come with varying number of instances in realistic settings, the existing meta-learning approaches for few-shot classfication assume even task distributions where the number of instances for each task and class are fixed. Due to such restriction, they learn to equally utilize the meta-knowledge across all the tasks, even when the number of instances per task and class largely varies. Moreover, they do not consider distributional difference in unseen tasks at the meta-test time, on which the meta-knowledge may have varying degree of usefulness depending on the task relatedness. To overcome these limitations, we propose a novel meta-learning model that adaptively balances the effect of the meta-learning and task-specific learning, and also class-specific learning within each task. Through the learning of the balancing variables, we can decide whether to obtain a solution close to the initial parameter or far from it. We formulate this objective into a Bayesian inference framework and solve it using variational inference. Our Bayesian Task-Adaptive Meta-Learning (Bayesian-TAML) significantly outperforms existing meta-learning approaches on benchmark datasets for both few-shot and realistic class- and task-imbalanced datasets, with especially higher gains on the latter. …