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-articleJuly 2024
Dismantling complex networks with graph contrastive learning and multi-hop aggregation
Information Sciences: an International Journal (ISCI), Volume 676, Issue CAug 2024https://doi.org/10.1016/j.ins.2024.120780AbstractNetwork dismantling is a process of identifying influential nodes that can decompose a network into disconnected sub-networks. This provides a novel approach to understanding and analyzing complex networks abstracted from the real world. State-of-...
- research-articleJuly 2024
Open knowledge base canonicalization with multi-task learning
AbstractThe construction of large open knowledge bases (OKBs) is integral to many knowledge-driven applications on the world wide web such as web search. However, noun phrases in OKBs often suffer from redundancy and ambiguity, which calls for the ...
- research-articleJune 2024
Load Balanced PIM-Based Graph Processing
ACM Transactions on Design Automation of Electronic Systems (TODAES), Volume 29, Issue 4Article No.: 61, Pages 1–22https://doi.org/10.1145/3659951Graph processing is widely used for many modern applications, such as social networks, recommendation systems, and knowledge graphs. However, processing large-scale graphs on traditional Von Neumann architectures is challenging due to the irregular graph ...
- research-articleJuly 2024
CL&CD: Contrastive Learning and Cluster Description for Zero-Shot Relation Extraction
Knowledge-Based Systems (KNBS), Volume 293, Issue CJun 2024https://doi.org/10.1016/j.knosys.2024.111652AbstractZero-shot Relation Extraction (ZRE) is designed to identify new relations when the model is adapted to a new environment in a new domain. The majority of existing ZRE methods employ distant supervision for data labeling, which inevitably leads ...
I/O Efficient Label-Constrained Reachability Queries in Large Graphs
Proceedings of the VLDB Endowment (PVLDB), Volume 17, Issue 10Pages 2590–2602https://doi.org/10.14778/3675034.3675049Computing the reachability between two vertices in a graph is a fundamental problem in graph data analysis. Most of the existing works assume that the edges in the graph have no labels, but in many real application scenarios, edges naturally come with ...
-
- short-paperJuly 2024
OSPC: OCR-Assisted VLM for Zero-Shot Harmful Meme Detection
WWW '24: Companion Proceedings of the ACM on Web Conference 2024May 2024, Pages 1904–1907https://doi.org/10.1145/3589335.3665994Harmful memes refer to the memes which contain social bias towards a certain group, such as gender, race, disabilities and so on. Detecting these harmful memes requires the model to have both visual and linguistic understanding of memes and some external ...
- research-articleJuly 2024
Improving efficiency and accuracy of levee hazard detection with deep learning
Computers & Geosciences (CGEO), Volume 187, Issue CMay 2024https://doi.org/10.1016/j.cageo.2024.105593AbstractThis paper presents a model framework based on a deep learning algorithm using Faster R-CNN to improve the accuracy and efficiency of detecting long-distance levee hazards. The proposed method aims to assist technicians in identifying hazards in ...
Highlights- A levee hazard detection model is built on the Faster R–CNN for position and prediction.
- The model replaces manual identification, enhancing efficiency and accuracy in identifying hazards.
- The self-made dataset, constructed from ...
- research-articleApril 2024
Few-shot Learning for Heterogeneous Information Networks
ACM Transactions on Information Systems (TOIS), Volume 42, Issue 4Article No.: 107, Pages 1–24https://doi.org/10.1145/3649311Heterogeneous information networks (HINs) are a key resource in many domain-specific retrieval and recommendation scenarios and in conversational environments. Current approaches to mining graph data often rely on abundant supervised information. However, ...
- research-articleJanuary 2024
Multiplex heterogeneous network representation learning with unipath based global awareness neural network
Future Generation Computer Systems (FGCS), Volume 150, Issue CJan 2024, Pages 317–325https://doi.org/10.1016/j.future.2023.09.007AbstractNetwork embedding has gained great popularity in tackling various network analytical tasks, such as link prediction and node classification. However, most existing works from heterogeneous networks ignore the relation heterogeneity with multiplex ...
Highlights- Many existing methods fail to effectively acquire information from heterogeneous networks.
- An attributed multiplex heterogeneous network embedding method is proposed.
- Proposed method utilizes the unipath network to modeling ...
- research-articleMarch 2024
On security performance analysis of IRS-aided VLC/RF hybrid system
Physical Communication (PHYCOM), Volume 61, Issue CDec 2023https://doi.org/10.1016/j.phycom.2023.102176AbstractIntelligent reflecting surface (IRS) has been introduced into wireless communication to improve physical layer security (PLS) due to its ability of reconfiguring propagation environments. However, most current research on IRS-aided PLS is for ...
- research-articleFebruary 2024
DC-SiamNet: Deep contrastive Siamese network for self-supervised MRI reconstruction
Computers in Biology and Medicine (CBIM), Volume 167, Issue CDec 2023https://doi.org/10.1016/j.compbiomed.2023.107619AbstractReconstruction methods based on deep learning have greatly shortened the data acquisition time of magnetic resonance imaging (MRI). However, these methods typically utilize massive fully sampled data for supervised training, restricting their ...
Highlights- We introduce contrastive learning and propose a DC-SiamNet that combines the Siamese framework and the deep unrolled network.
- We design a U-shape Regularization Unit with AWAPM (URUA) to obtain the relevant representation vector, in ...
- research-articleNovember 2023
Cross-view graph contrastive learning with hypergraph
AbstractGraph contrastive learning (GCL) provides a new perspective to alleviate the reliance on labeled data for graph representation learning. Recent efforts on GCL leverage various graph augmentation strategies, i.e., node dropping and edge masking, ...
Highlights- We proposed that hypergraphs are used as a paradigm to enhance graph contrastive learning.
- We propose a novel diffusion model-based fusion mechanism that aligns the positive examples.
- Our experimental results all exceed existing ...
- research-articleOctober 2023
MGICL: Multi-Grained Interaction Contrastive Learning for Multimodal Named Entity Recognition
CIKM '23: Proceedings of the 32nd ACM International Conference on Information and Knowledge ManagementOctober 2023, Pages 639–648https://doi.org/10.1145/3583780.3614967Multimodal Named Entity Recognition (MNER) aims to combine data from different modalities (e.g. text, images, videos, etc.) for recognition and classification of named entities, which is crucial for constructing Multimodal Knowledge Graphs (MMKGs). ...
- research-articleOctober 2023
Interpretable Fake News Detection with Graph Evidence
CIKM '23: Proceedings of the 32nd ACM International Conference on Information and Knowledge ManagementOctober 2023, Pages 659–668https://doi.org/10.1145/3583780.3614936Automatic detection of fake news has received widespread attentions over recent years. A pile of efforts has been put forward to address the problem with high accuracy, while most of them lack convincing explanations, making it difficult to curb the ...
- ArticleNovember 2023
- research-articleAugust 2023
<inline-formula><tex-math notation="LaTeX">$\mathsf{PF\text{-}HIN}$</tex-math></inline-formula>:Pre-Training for Heterogeneous Information Networks
IEEE Transactions on Knowledge and Data Engineering (IEEECS_TKDE), Volume 35, Issue 8Aug. 2023, Pages 8372–8385https://doi.org/10.1109/TKDE.2022.3206597In network representation learning we learn how to represent heterogeneous information networks in a low-dimensional space so as to facilitate effective search, classification, and prediction solutions. Previous network representation learning methods ...
- research-articleJuly 2023
Personalized Federated Relation Classification over Heterogeneous Texts
SIGIR '23: Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information RetrievalJuly 2023, Pages 973–982https://doi.org/10.1145/3539618.3591748Relation classification detects the semantic relation between two annotated entities from a piece of text, which is a useful tool for structurization of knowledge. Recently, federated learning has been introduced to train relation classification models ...
- research-articleJuly 2023
AugPrompt: Knowledgeable augmented-trigger prompt for few-shot event classification
Information Processing and Management: an International Journal (IPRM), Volume 60, Issue 4Jul 2023https://doi.org/10.1016/j.ipm.2022.103153AbstractFew-Shot Event Classification (FSEC) aims at assigning event labels to unlabeled sentences when limited annotated samples are available. Existing works mainly focus on using meta-learning to overcome the low-resource problem that still requires ...
Highlights- We apply a prompt-tuning-based method for few-shot event classification, which does not require abundantly seen classes.
- We design a task-specific template initializing strategy that can take all input factors into consideration.
- ...
- research-articleJune 2023
OpenFFT: An Adaptive Tuning Framework for 3D FFT on ARM Multicore CPUs
ICS '23: Proceedings of the 37th ACM International Conference on SupercomputingJune 2023, Pages 398–409https://doi.org/10.1145/3577193.3593735The sophisticated hierarchy and shared characteristics of cache in multicore CPU architectures bring challenges to the performance improvement of fundamental algorithms, especially in implementing and optimizing 3D FFT. 3D FFT is a memory-bounded ...