Learning vector representations (aka. embeddings) of users and items lies at the core of modern recommender systems. Ranging from early matrix factorization to recently emerged deep learning based methods, existing efforts typically obtain a user's (or an item's) embedding by mapping from pre-existing features that describe the user (or the item), such as ID and attributes. We argue that an inherent drawback of such methods is that, the collaborative signal, which is latent in user-item interactions, is not encoded in the embedding process. As such, the resultant embeddings may not be sufficient to capture the collaborative filtering effect.In this work, we propose to integrate the user-item interactionsmore specifically the bipartite graph structure -into the embedding process. We develop a new recommendation framework Neural Graph Collaborative Filtering (NGCF), which exploits the useritem graph structure by propagating embeddings on it. This leads to the expressive modeling of high-order connectivity in useritem graph, effectively injecting the collaborative signal into the embedding process in an explicit manner. We conduct extensive experiments on three public benchmarks, demonstrating significant improvements over several state-of-the-art models like HOP-Rec [39] and Collaborative Memory Network [5]. Further analysis verifies the importance of embedding propagation for learning better user and item representations, justifying the rationality and effectiveness of NGCF. Codes are available at https://github.com/ xiangwang1223/neural_graph_collaborative_filtering. CCS CONCEPTS• Information systems → Recommender systems.

LRRC8 volume-regulated anion channels transmit cGAMP into the bystander cells for interferon response and reinforcement of anti-viral defense

Abstract-Fast and reliable DC fault detection is one of the main challenges for modular multilevel converter (MMC) based DC grid with DC circuit breakers (DCCBs). This paper extracts the high frequency components of transient voltages by wavelet transform and proposes a fault identification method based on the difference of transient voltages to identify the faulted lines for DC grids using overhead lines. Meanwhile, a faulted pole discrimination method based on the difference between the change of positive and negative pole voltages is presented. A line protection scheme including detection activation, fault identification, faulted pole discrimination and post-fault re-closing is designed. Using only the local measurements, the scheme can realize the protection of the whole line without communication and has the capability of fault resistance endurance and anti-disturbance. The proposed method is tested with a four-terminal MMC based DC grid in PSCAD/EMTDC. The selection methods of threshold values are presented and the impact of DCCB operation on the reliability of DC fault protection is analysed. Simulation results verify the fast detection and reliability of the designed DC line protection scheme. Index Terms-DC fault protection, fault identification, transient voltage, hybrid DC breaker, modular multilevel converter (MMC), post-fault re-closing.This paper is a post-print of a paper submitted to and accepted for publication in IEEE Transaction on Power Delivery and is subject to Institution of Electrical and Electronic Engineering