Heterogeneous information network (HIN) contains multiple types of entities and relations. Most of existing HIN embedding methods learn the semantic information based on the heterogeneous structures between different entities, which are implicitly assumed to be complete. However, in real world, it is common that some relations are partially observed due to privacy or other reasons, resulting in a sparse network, in which the structure may be incomplete, and the ”unseen” links may also be positive due to the missing relations in data collection. To address this problem, we propose a novel and principled approach: a Multi-View Adversarial Completion Model (MV-ACM). Each relation space is characterized in a single viewpoint, enabling us to use the topological structural information in each view. Based on the multi-view architecture, an adversarial learning process is utilized to learn the reciprocity (i.e., complementary information) between different relations: In the generator, MV-ACM generates the complementary views by computing the similarity of the semantic representation of the same node in different views; while in the discriminator, MV-ACM discriminates whether the view is complementary by the topological structural similarity. Then we update the node’s semantic representation by aggregating neighborhoods information from the syncretic views. We conduct systematical experiments1 on six real-world networks from varied domains: AMiner, PPI, YouTube, Twitter, Amazon and Alibaba. Empirical results show that MV-ACM significantly outperforms the state-of-the-art approaches for both link prediction and node classification tasks.

In order to solve the excitation and position sensor installment problems for the brushless synchronous machine(BSM) used as starter/generator in the variable frequency AC power system of the civil aircraft, this paper presents a novel integrated method of AC excitation and high frequency injection for the sensorless starting control of BSM. The fixed three-phase 400Hz AC power is adopted for the three phase AC excitation of BSM in the initial starting process, where the three-phase exciter works as the rotation transformer, and the resulting 6thvoltage harmonics determined by the rotating rectifier are utilized as the high frequency voltage injected into the field-winding of main generator, then the rotor position is estimated by the high frequency voltage response signals extracted from the armature windings of main generator. The frequency-insensitive asynchronous demodulation strategy is proposed for rotor position estimation, and the initial rotor position is calibrated by the polarity of induced currents of armature windings within the establishment procedure of field excitation at standstill. Finally, the excitation effect and accuracy of the position detection algorithm for BSM is validated by the simulation results.