Search Results for author: Evgeny Kharlamov

Found 19 papers, 9 papers with code

GRAND+: Scalable Graph Random Neural Networks

1 code implementation12 Mar 2022 Wenzheng Feng, Yuxiao Dong, Tinglin Huang, Ziqi Yin, Xu Cheng, Evgeny Kharlamov, Jie Tang

In this work, we present a scalable and high-performance GNN framework GRAND+ for semi-supervised graph learning.

Data Augmentation Graph Learning +1

SelfKG: Self-Supervised Entity Alignment in Knowledge Graphs

1 code implementation2 Mar 2022 Xiao Liu, Haoyun Hong, Xinghao Wang, Zeyi Chen, Evgeny Kharlamov, Yuxiao Dong, Jie Tang

We present SelfKG with efficient strategies to optimize this objective for aligning entities without label supervision.

Entity Alignment Knowledge Graphs +1

Adaptive Diffusion in Graph Neural Networks

no code implementations NeurIPS 2021 Jialin Zhao, Yuxiao Dong, Ming Ding, Evgeny Kharlamov, Jie Tang

Notably, message passing based GNNs, e. g., graph convolutional networks, leverage the immediate neighbors of each node during the aggregation process, and recently, graph diffusion convolution (GDC) is proposed to expand the propagation neighborhood by leveraging generalized graph diffusion.

SegTime: Precise Time Series Segmentation without Sliding Window

no code implementations29 Sep 2021 Li Zeng, Baifan Zhou, Mohammad Al-Rifai, Evgeny Kharlamov

We propose a neural networks approach SegTime that finds precise breakpoints, obviates sliding windows, handles long-term dependencies, and it is insensitive to the label changing frequency.

On Event-Driven Knowledge Graph Completion in Digital Factories

no code implementations8 Sep 2021 Martin Ringsquandl, Evgeny Kharlamov, Daria Stepanova, Steffen Lamparter, Raffaello Lepratti, Ian Horrocks, Peer Kröger

Smooth operation of such factories requires that the machines and engineering personnel that conduct their monitoring and diagnostics share a detailed common industrial knowledge about the factory, e. g., in the form of knowledge graphs.

Knowledge Graph Completion

GCCAD: Graph Contrastive Coding for Anomaly Detection

1 code implementation17 Aug 2021 Bo Chen, Jing Zhang, Xiaokang Zhang, Yuxiao Dong, Jian Song, Peng Zhang, Kaibo Xu, Evgeny Kharlamov, Jie Tang

To achieve the contrastive objective, we design a graph neural network encoder that can infer and further remove suspicious links during message passing, as well as learn the global context of the input graph.

Anomaly Detection Feature Engineering

A Self-supervised Method for Entity Alignment

1 code implementation17 Jun 2021 Xiao Liu, Haoyun Hong, Xinghao Wang, Zeyi Chen, Evgeny Kharlamov, Yuxiao Dong, Jie Tang

We present SelfKG by leveraging this discovery to design a contrastive learning strategy across two KGs.

Contrastive Learning Entity Alignment +2

TDGIA:Effective Injection Attacks on Graph Neural Networks

1 code implementation12 Jun 2021 Xu Zou, Qinkai Zheng, Yuxiao Dong, Xinyu Guan, Evgeny Kharlamov, Jialiang Lu, Jie Tang

In the GIA scenario, the adversary is not able to modify the existing link structure and node attributes of the input graph, instead the attack is performed by injecting adversarial nodes into it.

Neural Entity Summarization with Joint Encoding and Weak Supervision

1 code implementation1 May 2020 Junyou Li, Gong Cheng, Qingxia Liu, Wen Zhang, Evgeny Kharlamov, Kalpa Gunaratna, Huajun Chen

In a large-scale knowledge graph (KG), an entity is often described by a large number of triple-structured facts.

On Expansion and Contraction of DL-Lite Knowledge Bases

no code implementations25 Jan 2020 Dmitriy Zheleznyakov, Evgeny Kharlamov, Werner Nutt, Diego Calvanese

Moreover, we show that well-known formula-based approaches are also not appropriate for DL-Lite expansion and contraction: they either have a high complexity of computation, or they produce logical theories that cannot be expressed in DL-Lite.

On Equivalence and Cores for Incomplete Databases in Open and Closed Worlds

no code implementations14 Jan 2020 Henrik Forssell, Evgeny Kharlamov, Evgenij Thorstensen

However, for Closed Powerset semantics we show that one can find, for any incomplete database, a unique finite set of its subinstances which are subinstances (up to renaming of nulls) of all instances semantically equivalent to the original incomplete one.

A Framework for Evaluating Snippet Generation for Dataset Search

no code implementations2 Jul 2019 Xiaxia Wang, Jinchi Chen, Shuxin Li, Gong Cheng, Jeff Z. Pan, Evgeny Kharlamov, Yuzhong Qu

Reusing existing datasets is of considerable significance to researchers and developers.

Towards Analytics Aware Ontology Based Access to Static and Streaming Data (Extended Version)

no code implementations18 Jul 2016 Evgeny Kharlamov, Yannis Kotidis, Theofilos Mailis, Christian Neuenstadt, Charalampos Nikolaou, Özgür Özcep, Christoforos Svingos, Dmitriy Zheleznyakov, Sebastian Brandt, Ian Horrocks, Yannis Ioannidis, Steffen Lamparter, Ralf Möller

Real-time analytics that requires integration and aggregation of heterogeneous and distributed streaming and static data is a typical task in many industrial scenarios such as diagnostics of turbines in Siemens.

Controlled Query Evaluation for Datalog and OWL 2 Profile Ontologies

no code implementations24 Apr 2015 Bernardo Cuenca Grau, Evgeny Kharlamov, Egor V. Kostylev, Dmitriy Zheleznyakov

We study confidentiality enforcement in ontologies under the Controlled Query Evaluation framework, where a policy specifies the sensitive information and a censor ensures that query answers that may compromise the policy are not returned.

Verification of Inconsistency-Aware Knowledge and Action Bases (Extended Version)

no code implementations23 Apr 2013 Diego Calvanese, Evgeny Kharlamov, Marco Montali, Ario Santoso, Dmitriy Zheleznyakov

Description Logic Knowledge and Action Bases (KABs) have been recently introduced as a mechanism that provides a semantically rich representation of the information on the domain of interest in terms of a DL KB and a set of actions to change such information over time, possibly introducing new objects.

Cannot find the paper you are looking for? You can Submit a new open access paper.