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
Manifold-based multi-graph embedding for semi-supervised classification
Pattern Recognition Letters (PTRL), Volume 182, Issue CJun 2024, Pages 53–59https://doi.org/10.1016/j.patrec.2024.04.003AbstractGraph semi-supervised learning (GSSL) plays an important role in semi-supervised classification by leveraging the similarity of graph topology and convex optimization with Laplacian-based regularization. Current approaches mainly focus on data ...
Highlights- A novel manifold-based multi-graph embedding (M2GE) is proposed for semi-supervised classification.
- Multi-sampling augmentation is employed to improve the generalization of the model.
- M2GE effectively improves the accuracy rate of ...
- research-articleJune 2024
A Hybrid Few-Shot Image Classification Framework Combining Gaussian Modeling and Label Propagation
ICMR '24: Proceedings of the 2024 International Conference on Multimedia RetrievalMay 2024, Pages 628–637https://doi.org/10.1145/3652583.3658114Humans possess the remarkable ability to recognize new objects with merely a handful of labeled examples, whereas contemporary deep learning models continue to face challenges in few-shot learning scenarios, primarily due to the scarcity of training ...
- research-articleJune 2024
Multi-modal Entity Alignment via Position-enhanced Multi-label Propagation
ICMR '24: Proceedings of the 2024 International Conference on Multimedia RetrievalMay 2024, Pages 366–375https://doi.org/10.1145/3652583.3658085Multi-modal Entity Alignment (MMEA) refers to utilizing multiple modalities such as text, images, videos, etc., to match entities from multiple knowledge graphs. Compared to single-modal entity alignment, multi-modal entity alignment can provide a more ...
- research-articleMarch 2024
Efficient, Direct, and Restricted Black-Box Graph Evasion Attacks to Any-Layer Graph Neural Networks via Influence Function
WSDM '24: Proceedings of the 17th ACM International Conference on Web Search and Data MiningMarch 2024, Pages 693–701https://doi.org/10.1145/3616855.3635826Graph neural network (GNN), the mainstream method to learn on graph data, is vulnerable to graph evasion attacks, where an attacker slightly perturbing the graph structure can fool trained GNN models. Existing work has at least one of the following ...
- short-paperMarch 2024
NI-MLA: Node Importance based Multi-level Label Assignment strategy for community detection in sparse social graphs
ASONAM '23: Proceedings of the 2023 IEEE/ACM International Conference on Advances in Social Networks Analysis and MiningNovember 2023, Pages 281–285https://doi.org/10.1145/3625007.3627598This research paper addresses the challenge of detecting communities in sparse social graphs and presents a novel approach that leverages node importance and label propagation. The proposed method consists of three phases: initialization, label ...
-
- research-articleOctober 2023
Chaos to Order: A Label Propagation Perspective on Source-Free Domain Adaptation
MM '23: Proceedings of the 31st ACM International Conference on MultimediaOctober 2023, Pages 2877–2887https://doi.org/10.1145/3581783.3613821Source-free domain adaptation (SFDA), where only a pre-trained source model is used to adapt to the target distribution, is a more general approach to achieving domain adaptation in the real world. However, it can be challenging to capture the inherent ...
- research-articleOctober 2023
Enhancing Fake News Detection in Social Media via Label Propagation on Cross-modal Tweet Graph
MM '23: Proceedings of the 31st ACM International Conference on MultimediaOctober 2023, Pages 2400–2408https://doi.org/10.1145/3581783.3612086Fake news detection in social media has become increasingly important due to the rapid proliferation of personal media channels and the consequential dissemination of misleading information. Existing methods, which primarily rely on multimodal features ...
- research-articleAugust 2023
Gravitational clustering algorithm based on mutual K-nearest neighbors
AI2A '23: Proceedings of the 2023 3rd International Conference on Artificial Intelligence, Automation and AlgorithmsJuly 2023, Pages 79–85https://doi.org/10.1145/3611450.3611462To address the problems of difficulty in determining the truncation distance, single definition of local density and low robustness of non-centroid assignment strategy and chain reaction in density peaking clustering algorithm (DPC), this paper proposes ...
- research-articleJuly 2023
Complementary Coarse-to-Fine Matching for Video Object Segmentation
ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), Volume 19, Issue 6Article No.: 203, Pages 1–21https://doi.org/10.1145/3596496Semi-supervised Video Object Segmentation (VOS) needs to establish pixel-level correspondences between a video frame and preceding segmented frames to leverage their segmentation clues. Most works rely on features at a single scale to establish those ...
- research-articleDecember 2022
SDNMF: Semisupervised discriminative nonnegative matrix factorization for feature learning
International Journal of Intelligent Systems (IJIS), Volume 37, Issue 12December 2022, Pages 11547–11581https://doi.org/10.1002/int.23054AbstractAs one of the most effective feature learning methods, Nonnegative Matrix Factorization (NMF) has been widely used in many scientific fields, such as computer vision, data mining, and bioinformatics. However, NMF is an unsupervised method that ...
- research-articleDecember 2022
Asymmetric Label Propagation for Video Object Segmentation
MMAsia '22: Proceedings of the 4th ACM International Conference on Multimedia in AsiaDecember 2022, Article No.: 3, Pages 1–7https://doi.org/10.1145/3551626.3564943Semi-supervised video object segmentation aims to segment foreground objects across a video sequence based on their masks given at the first frame. The motion in adjacent frames tends to be smooth, yet object appearances could change substantially in ...
- research-articleDecember 2022
Direction-optimizing Label Propagation Framework for Structure Detection in Graphs: Design, Implementation, and Experimental Analysis
ACM Journal of Experimental Algorithmics (JEA), Volume 27Article No.: 1.12, Pages 1–31https://doi.org/10.1145/3564593Label Propagation is not only a well-known machine learning algorithm for classification but also an effective method for discovering communities and connected components in networks. We propose a new Direction-optimizing Label Propagation Algorithm (...
- research-articleJune 2023
TSPA: Efficient Target-Stance Detection on Twitter
ASONAM '22: Proceedings of the 2022 IEEE/ACM International Conference on Advances in Social Networks Analysis and MiningNovember 2022, Pages 242–246https://doi.org/10.1109/ASONAM55673.2022.10068608Target-stance detection on large-scale datasets is a core component of many of the most common stance detection applications. However, despite progress in recent years, stance detection research primarily occurs at the document-level on small-scale ...
- short-paperOctober 2022
SmartQuery: An Active Learning Framework for Graph Neural Networks through Hybrid Uncertainty Reduction
CIKM '22: Proceedings of the 31st ACM International Conference on Information & Knowledge ManagementOctober 2022, Pages 4199–4203https://doi.org/10.1145/3511808.3557701Graph neural networks have achieved significant success in representation learning. However, the performance gains come at a cost; acquiring comprehensive labeled data for training can be prohibitively expensive. Active learning mitigates this issue by ...
- research-articleAugust 2022
SciNoBo: A Hierarchical Multi-Label Classifier of Scientific Publications
WWW '22: Companion Proceedings of the Web Conference 2022April 2022, Pages 800–809https://doi.org/10.1145/3487553.3524677Classifying scientific publications according to Field-of-Science (FoS) taxonomies is of crucial importance, allowing funders, publishers, scholars, companies and other stakeholders to organize scientific literature more effectively. Most existing ...
- short-paperApril 2022
Sampling-based Label Propagation for Balanced Graph Partitioning
ICPE '22: Proceedings of the 2022 ACM/SPEC on International Conference on Performance EngineeringApril 2022, Pages 223–230https://doi.org/10.1145/3489525.3511698In this experience paper, we present new sampling-based algorithms for balanced graph partitioning based on the Label Propagation (LP) approach. The purpose is to define new heuristics to extend the multi-objective and scalable Balanced GRAph ...
- research-articleJanuary 2022
Motif‐based embedding label propagation algorithm for community detection
International Journal of Intelligent Systems (IJIS), Volume 37, Issue 3March 2022, Pages 1880–1902https://doi.org/10.1002/int.22759AbstractCommunity detection can exhibit the aggregation behavior of complex networks. Network motifs are the fundamental building blocks which can reveal the higher‐order structure of complex networks. Label propagation algorithm has the advantage of ...
- research-articleJanuary 2022
A new fault isolation approach based on propagated nonnegative matrix factorizations
Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology (JIFS), Volume 43, Issue 42022, Pages 4271–4284https://doi.org/10.3233/JIFS-212590To address the challenging fault isolation problem, this paper proposes a new fault isolation approach based on propagated nonnegative matrix factorizations (PNMFs). PNMFs make significant contributions to the theoretical research on nonnegative matrix ...
- research-articleJanuary 2022
A cluster and label approach for classifying imbalanced data streams in the presence of scarcely labelled data
International Journal of Business Intelligence and Data Mining (IJBIDM), Volume 21, Issue 42022, Pages 443–464https://doi.org/10.1504/ijbidm.2022.126503Classifying imbalanced data streams is often a challenging task primarily due to the continuous flow of infinite data and due to the unavailability of class labels. The problem is two-fold when the stream is imbalanced in nature. Due to the ...
- research-articleJanuary 2022
Big graph partitioning
Procedia Computer Science (PROCS), Volume 203, Issue C2022, Pages 789–794https://doi.org/10.1016/j.procs.2022.07.118AbstractAt many levels, from storage infrastructures to programming paradigms, billion-node graphs pose considerable obstacles. It is necessary to provide a general-purpose graph-processing platform. A distributed memory system is thought to be a viable ...