Search for: All records

Multi-graph clustering aims to improve clustering accuracy by leveraging information from different domains, which has been shown to be extremely effective for achieving better clustering results than single graph based clustering algorithms. Despite the previous success, existing multi-graph clustering methods mostly use shallow models, which are incapable to capture the highly non-linear structures and the complex cluster associations in multigraph, thus result in sub-optimal results. Inspired by the powerful representation learning capability of neural networks, in this paper, we propose an end-to-end deep learning model to simultaneously infer cluster assignments and cluster associations in multi-graph. Specifically, we use autoencoding networks to learn node embeddings. Meanwhile, we propose a minimum-entropy based clustering strategy to cluster nodes in the embedding space for each graph. We introduce two regularizers to leverage both within-graph and cross-graph dependencies. An attentive mechanism is further developed to learn cross-graph cluster associations. Through extensive experiments on a variety of datasets, we observe that our method outperforms state-of-the-art baselines by a large margin. 

Frost heave can cause serious damage to civil infrastructure. For example, interactions of soil and water pipes under frozen conditions have been found to significantly accelerate pipe fracture. Frost heave may cause the retaining walls along highways to crack and even fail in cold climates. This paper describes a holistic model to simulate the temperature, stress, and deformation in frozen soil and implement a model to simulate frost heave and stress on water pipelines. The frozen soil behaviors are based on a microstructure-based random finite element model, which holistically describes the mechanical behaviors of soils subjected to freezing conditions. The new model is able to simulate bulk behaviors by considering the microstructure of soils. The soil is phase coded and therefore the simulation model only needs the corresponding parameters of individual phases. This significantly simplifies obtaining the necessary parameters for the model. The capability of the model in simulating the temperature distribution and volume change are first validated with laboratory scale experiments. Coupled thermal-mechanical processes are introduced to describe the soil responses subjected to sub-zero temperature on the ground surface. This subsequently changes the interaction modes between ground and water pipes and leads to increase of stresses on the water pipes. The effects of cracks along a water pipe further cause stress concentration, which jeopardizes the pipe’s performance and leads to failure. The combined effects of freezing ground and traffic load are further evaluated with the model.