Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleAugust 2023
Few-shot Low-resource Knowledge Graph Completion with Multi-view Task Representation Generation
KDD '23: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data MiningAugust 2023, Pages 1862–1871https://doi.org/10.1145/3580305.3599350Despite their capacity to convey knowledge, most existing knowledge graphs (KGs) are created for specific domains using low-resource data sources, especially those in non-global languages, and thus unavoidably suffer from the incompleteness problem. The ...
- research-articleAugust 2023
Counterfactual Learning on Heterogeneous Graphs with Greedy Perturbation
KDD '23: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data MiningAugust 2023, Pages 2988–2998https://doi.org/10.1145/3580305.3599289Due to the growing importance of using graph neural networks in high-stakes applications, there is a pressing need to interpret the predicted results of these models. Existing methods for explanation have mainly focused on generating sub-graphs ...
- research-articleFebruary 2023
Interpretable Research Interest Shift Detection with Temporal Heterogeneous Graphs
WSDM '23: Proceedings of the Sixteenth ACM International Conference on Web Search and Data MiningFebruary 2023, Pages 321–329https://doi.org/10.1145/3539597.3570453Researchers dedicate themselves to research problems they are interested in and often have evolving research interests in their academic careers. The study of research interest shift detection can help to find facts relevant to scientific training paths, ...
- research-articleFebruary 2023
Cross-domain few-shot graph classification with a reinforced task coordinator
AAAI'23/IAAI'23/EAAI'23: Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence and Thirty-Fifth Conference on Innovative Applications of Artificial Intelligence and Thirteenth Symposium on Educational Advances in Artificial IntelligenceFebruary 2023, Article No.: 546, Pages 4893–4901https://doi.org/10.1609/aaai.v37i4.25615Cross-domain graph few-shot learning attempts to address the prevalent data scarcity issue in graph mining problems. However, the utilization of cross-domain data induces another intractable domain shift issue which severely degrades the generalization ...
- research-articleAugust 2022
Multi-scale self-attention generative adversarial network for pathology image restoration
The Visual Computer: International Journal of Computer Graphics (VISC), Volume 39, Issue 9Sep 2023, Pages 4305–4321https://doi.org/10.1007/s00371-022-02592-1AbstractHigh-quality histopathology images are significant for accurate diagnosis and symptomatic treatment. However, local cross-contamination or missing data are common phenomena due to many factors, such as the superposition of foreign bodies and ...
-
- research-articleAugust 2022
Few-shot Heterogeneous Graph Learning via Cross-domain Knowledge Transfer
KDD '22: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data MiningAugust 2022, Pages 2450–2460https://doi.org/10.1145/3534678.3539431Graph few-shot learning seeks to alleviate the label scarcity problem resulting from the difficulties and high cost of data annotations in graph learning. However, the overwhelming solutions in graph few-shot learning focus on homogeneous graphs, ...
- research-articleFebruary 2022
Interpretable Relation Learning on Heterogeneous Graphs
WSDM '22: Proceedings of the Fifteenth ACM International Conference on Web Search and Data MiningFebruary 2022, Pages 1266–1274https://doi.org/10.1145/3488560.3498508Relation learning, widely used in recommendation systems or relevant entity search over knowledge graphs, has attracted increasing attentions in recent years. Existing methods like network embedding and graph neural networks (GNNs), learn the node ...
- research-articleJanuary 2020
Recurrent Attention Walk for Semi-supervised Classification
WSDM '20: Proceedings of the 13th International Conference on Web Search and Data MiningJanuary 2020, Pages 16–24https://doi.org/10.1145/3336191.3371853In this paper, we study the graph-based semi-supervised learning for classifying nodes in attributed networks, where the nodes and edges possess content information. Recent approaches like graph convolution networks and attention mechanisms have been ...
- ArticleNovember 2013
An Intelligent Anomaly Detection and Reasoning Scheme for VM Live Migration via Cloud Data Mining
ICTAI '13: Proceedings of the 2013 IEEE 25th International Conference on Tools with Artificial IntelligenceNovember 2013, Pages 412–419https://doi.org/10.1109/ICTAI.2013.68Cloud computing operators provide flexible, convenient, and affordable means to access public and private services. Virtual machine (VM) live migration, as an important feature of virtualization technique in cloud computing, ensures high efficiency and ...
- ArticleJuly 2013
An LOF-Based Adaptive Anomaly Detection Scheme for Cloud Computing
COMPSACW '13: Proceedings of the 2013 IEEE 37th Annual Computer Software and Applications Conference WorkshopsJuly 2013, Pages 206–211https://doi.org/10.1109/COMPSACW.2013.28One of the most attractive things about cloud computing from the perspective of business people is that it provides an effective means to outsource IT. The behaviors of business applications on cloud are constantly evolving due to technical upgrading, ...
- ArticleJuly 2013
A Multi-order Markov Chain Based Scheme for Anomaly Detection
COMPSACW '13: Proceedings of the 2013 IEEE 37th Annual Computer Software and Applications Conference WorkshopsJuly 2013, Pages 83–88https://doi.org/10.1109/COMPSACW.2013.12This paper presents a feasible multi-order Markov chain based scheme for anomaly detection in server systems. In our approach, both the high-order Markov chain and multivariate time series are taken into account, along with the detailed design of ...
- ArticleJune 2012
A Case Study of CPNS Intelligence: Provenance Reasoning over Tracing Cross Contamination in Food Supply Chain
ICDCSW '12: Proceedings of the 2012 32nd International Conference on Distributed Computing Systems WorkshopsJune 2012, Pages 330–335https://doi.org/10.1109/ICDCSW.2012.67A Cyber-Physical System (CPS) is a system featuring a tight combination and coordination of the system's computational and physical elements. CPS integrates the executive ability of the physical world and the intelligence of the cyber world to add new ...
- ArticleMarch 2010
Study on PID neural network control system in the main electromotor of the fine rolling mill
CAR'10: Proceedings of the 2nd international Asia conference on Informatics in control, automation and robotics - Volume 2March 2010, Pages 143–146The author analyzed the properties of a DC motor speed regulation system of rolling machine in the paper. He adopted PID neural network to form self-learning double loop closed DC moor speed regulating system. The forward and back-propagation are ...