Nowadays, E-commerce is increasingly integrated into our daily lives. Meanwhile, shopping process has also changed incrementally from one behavior (purchase) to multiple behaviors (such as view, carting and purchase). Therefore, utilizing interaction
data of auxiliary behavior data draws a lot of attention in the E-commerce recommender systems. However, all existing models ignore two kinds of intrinsic heterogeneity which are helpful to capture the difference of user preferences and the difference of item attributes. First (intra-heterogeneity), each user has multiple social identities with otherness, and these different identities can result in quite different interaction preferences. Second (inter-heterogeneity), each item can transfer an item-specific percentage of score from low-level behavior to high-level behavior for the gradual relationship among multiple behaviors. Thus, the lack of consideration of these heterogeneities damages recommendation rank performance. To model the above heterogeneities, we propose a novel method named intra- and inter-heterogeneity recommendation model (ARGO). Specifically, we embed each user into multiple vectors representing the users identities, and the maximum of identity scores indicates the interaction preference. Besides, we regard the item-specific transition percentage as trainable transition probability between different behaviors. Extensive experiments on two real-world datasets show that ARGO performs much better than the state-of-the-art in multi-behavior scenarios.
Accurate automatic liver and tumor segmentation plays a vital role in treatment planning and disease monitoring. Recently, deep convolutional neural network (DCNNs) has obtained tremendous success in 2D and 3D medical image segmentation. However, 2D
DCNNs cannot fully leverage the inter-slice information, while 3D DCNNs are computationally expensive and memory intensive. To address these issues, we first propose a novel dense-sparse training flow from a data perspective, in which, densely adjacent slices and sparsely adjacent slices are extracted as inputs for regularizing DCNNs, thereby improving the model performance. Moreover, we design a 2.5D light-weight nnU-Net from a network perspective, in which, depthwise separable convolutions are adopted to improve the efficiency. Extensive experiments on the LiTS dataset have demonstrated the superiority of the proposed method.
Electric power grids are critical infrastructure that support modern society by supplying electric energy to critical infrastructure systems. Incidents are increasing that range from natural disasters to cyber attacks. These incidents threaten the re
liability of power systems and create disturbances that affect the whole society. While existing standards and technologies are being applied to proactively improve power system reliability and resilience, there are still widespread electricity outages that cause billions of dollars in economic loss annually and threaten societal function and safety. Improving resilience in preparation for such events warrants strategic network design to harden the system. This paper presents an approach to strengthen power system security and reliability against disturbances by expanding the network structure from an ecosystems perspective. Ecosystems have survived a wide range of disturbances over a long time period, and an ecosystems robust structure has been identified as the key element for its survivability. In this paper, we first present a study of the correlation of ecological robustness and power system structures. Then, we present a mixed-integer nonlinear programming problem (MINLP) that expands the transmission network structure to maximize ecological robustness with power system constraints for an improved ability to absorb disturbances. We solve the MINLP problem for the IEEE 24 Bus Reliability Test System and three synthetic power grids with 200-, 500- and 2000-buses, respectively. Our evaluation results show the optimized power systems have increased the networks robustness, more equally distributed power flows, and less violations under different levels of contingencies.
Hashing has been widely used in approximate nearest neighbor search for its storage and computational efficiency. Deep supervised hashing methods are not widely used because of the lack of labeled data, especially when the domain is transferred. Mean
while, unsupervised deep hashing models can hardly achieve satisfactory performance due to the lack of reliable similarity signals. To tackle this problem, we propose a novel deep unsupervised hashing method, namely Distilled Smooth Guidance (DSG), which can learn a distilled dataset consisting of similarity signals as well as smooth confidence signals. To be specific, we obtain the similarity confidence weights based on the initial noisy similarity signals learned from local structures and construct a priority loss function for smooth similarity-preserving learning. Besides, global information based on clustering is utilized to distill the image pairs by removing contradictory similarity signals. Extensive experiments on three widely used benchmark datasets show that the proposed DSG consistently outperforms the state-of-the-art search methods.
Power system N-x contingency analysis has inherent challenges due to its combinatorial characteristic where outages grow exponentially with the increase of x and N. To address these challenges, this paper proposes a method that utilizes Line Outage D
istribution Factors (LODFs) and group betweenness centrality to identify subsets of critical branches. The proposed LODF metrics are used to select the high-impact branches. Based on each selected branch, the approach constructs the subgraph with parameters of distance and search level, while using branches LODF metrics as the weights. A key innovation of this work is the use of the distance and search level parameters, which allow the subgraph to identify the most coupled critical elements that may be far away from a selected branch. The proposed approach is validated using the 200- and 500-bus test cases, and results show that the proposed approach can identify multiple N-x contingencies that cause violations.
This paper presents a method to better integrate dynamic models for renewable resources into synthetic electric grids. An automated dynamic models assignment process is proposed for wind and solar generators. A realistic composition ratio for differe
nt types of wind turbine generators (WTG) is assigned to each wind generator. Statistics summarized from real electric grid data form the bases in assigning proper models with reasonable parameters to each WTG. A similar process is used to assign appropriate models and parameters to each photovoltaic (PV) generator. Multiple control strategies of the renewable resources are considered and tested in case studies. Two large-scale synthetic network test cases are used as examples of modeling the dynamics of renewable generators. Several transient stability metrics are adopted to assess the stability level after being subject to N-1 contingency event. Representative contingency events are given to demonstrate the performance of the synthetic renewable generator models.
Recently, hashing is widely used in approximate nearest neighbor search for its storage and computational efficiency. Most of the unsupervised hashing methods learn to map images into semantic similarity-preserving hash codes by constructing local se
mantic similarity structure from the pre-trained model as the guiding information, i.e., treating each point pair similar if their distance is small in feature space. However, due to the inefficient representation ability of the pre-trained model, many false positives and negatives in local semantic similarity will be introduced and lead to error propagation during the hash code learning. Moreover, few of the methods consider the robustness of models, which will cause instability of hash codes to disturbance. In this paper, we propose a new method named {textbf{C}}omprehensive s{textbf{I}}milarity {textbf{M}}ining and c{textbf{O}}nsistency lear{textbf{N}}ing (CIMON). First, we use global refinement and similarity statistical distribution to obtain reliable and smooth guidance. Second, both semantic and contrastive consistency learning are introduced to derive both disturb-invariant and discriminative hash codes. Extensive experiments on several benchmark datasets show that the proposed method outperforms a wide range of state-of-the-art methods in both retrieval performance and robustness.
MAX phases are a family of layered, hexagonal-structure ternary carbides or nitrides of a transitional metal and an A-group element. What makes this type of material fascinating and potentially useful is their remarkable combinations of metallic and
ceramic characteristics; as well as the indispensable role in top-down synthesis of their 2D counterparts, MXenes. To enhance the efficiency in the successful search for potential novel MAX phases, the main efforts could go toward creating an informationprediction system incorporating all MAX phases databases, as well as generally valid principles and the high-quality regularities. In this work, we employ structure mapping methodology, which has shown its merit of being useful guides in materials design, with Hume-Rothery parameters to provide guiding principles in the search of novel MAX phases. The formable/non-formable data on MAX phases can be ordered within a twodimensional plot by using proposed expression of geometrical and electron concentration factors.
