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-articleSeptember 2024
Escaping the neutralization effect of modality features fusion in multimodal Fake News Detection
AbstractFake news spreads at unprecedented speeds through online social media, raising many concerns and negative impacts on a variety of domains. To control this issue, Fake News Detection (FND) naturally becomes the chief task while multimodal FND has ...
Highlights- We describe the neutralization effect problem of previous multimodal FND methods.
- We propose a new model MINER-UVS with the PU learning and feature fusion techniques.
- Extensive experiments are conducted to indicate the ...
- research-articleAugust 2024
Exploiting multi-level consistency learning for source-free domain adaptation
AbstractDue to data privacy concerns, a more practical task known as Source-free Unsupervised Domain Adaptation (SFUDA) has gained significant attention recently. SFUDA adapts a pre-trained source model to the target domain without access to the source ...
- ArticleAugust 2024
Negative Samples Selection Can Improve Graph Contrastive Learning in Collaborative Filtering
Advanced Intelligent Computing Technology and ApplicationsPages 456–467https://doi.org/10.1007/978-981-97-5618-6_38AbstractNowadays, graph collaborative filtering is widely used in recommender system as an important technique. In order to alleviate the common data sparsity problem in collaborative filtering, contrastive learning techniques have been utilized to assist ...
- ArticleAugust 2024
Enhancing Dense Object Counting in Occlusion with a Dual-Branch Network
Advanced Intelligent Computing Technology and ApplicationsPages 121–132https://doi.org/10.1007/978-981-97-5612-4_11AbstractObject counting is a crucial technique that has wide-ranging applications in various domains. A significant challenge in this area is to accurately count dense objects in the presence of occlusions. Previous studies typically used single-branch ...
- ArticleAugust 2024
Domain-Knowledge Enhanced GANs for High-Quality Trajectory Generation
Advanced Intelligent Computing Technology and ApplicationsPages 386–396https://doi.org/10.1007/978-981-97-5606-3_33AbstractRealistically simulating human mobility and generating high-quality trajectories are essential for location-based applications like epidemic analysis, traffic management, and location privacy. Current trajectory generation techniques that are free ...
-
- research-articleJuly 2024
Unsupervised Sentence Representation Learning with Frequency-induced Adversarial tuning and Incomplete sentence filtering
AbstractPre-trained Language Model (PLM) is nowadays the mainstay of Unsupervised Sentence Representation Learning (USRL). However, PLMs are sensitive to the frequency information of words from their pre-training corpora, resulting in anisotropic ...
- research-articleJune 2024
Consensus representation-driven structured graph learning for multi-view clustering
Applied Intelligence (KLU-APIN), Volume 54, Issue 17-18Pages 8545–8562https://doi.org/10.1007/s10489-024-05616-6AbstractGraph-based multi-view clustering has gained increasing attention due to its ability to effectively unveil complex nonlinear structures among data points from various views. Nevertheless, prior studies usually focus on amalgamating multiple ...
- research-articleMay 2024
A Simple but Effective Approach for Unsupervised Few-Shot Graph Classification
WWW '24: Proceedings of the ACM Web Conference 2024Pages 4249–4259https://doi.org/10.1145/3589334.3645587Graphs, as a fundamental data structure, have proven efficacy in modeling complex relationships between objects and are therefore found in wide web applications. Graph classification is an essential task in graph data analysis, which can effectively ...
- research-articleFebruary 2024
Graph-based Text Classification by Contrastive Learning with Text-level Graph Augmentation
ACM Transactions on Knowledge Discovery from Data (TKDD), Volume 18, Issue 4Article No.: 77, Pages 1–21https://doi.org/10.1145/3638353Text Classification (TC) is a fundamental task in the information retrieval community. Nowadays, the mainstay TC methods are built on the deep neural networks, which can learn much more discriminative text features than the traditional shallow learning ...
- research-articleJuly 2024
GMFITD: Graph Meta-Learning for Effective Few-Shot Insider Threat Detection
IEEE Transactions on Information Forensics and Security (TIFS), Volume 19Pages 7161–7175https://doi.org/10.1109/TIFS.2024.3430106Insider threats represent a significant challenge in both corporate and governmental sectors. Most existing supervised learning based detection methods that rely on transforming user behavior into sequential data do not fully utilize structural ...
- research-articleNovember 2023
LaenNet: Learning robust GCNs by propagating labels
Neural Networks (NENE), Volume 168, Issue CPages 652–664https://doi.org/10.1016/j.neunet.2023.09.035AbstractGraph Convolutional Networks (GCNs) can be acknowledged as one of the most significant methodologies for graph representation learning, and the family of GCNs has recently achieved great success in the community. However, in real-world scenarios, ...
- research-articleOctober 2023
Unsupervised Aspect Term Extraction by Integrating Sentence-level Curriculum Learning with Token-level Self-paced Learning
CIKM '23: Proceedings of the 32nd ACM International Conference on Information and Knowledge ManagementPages 1982–1991https://doi.org/10.1145/3583780.3615103Aspect Term Extraction (ATE), a key sub-task of aspect-based sentiment analysis, aims to extract aspect terms from review sentences on which users express opinions. Existing studies mainly treat ATE as a sequence labeling problem, and the aspect terms of ...
- research-articleOctober 2023
Meta Auxiliary Learning for Top-K Recommendation
IEEE Transactions on Knowledge and Data Engineering (IEEECS_TKDE), Volume 35, Issue 10Pages 10857–10870https://doi.org/10.1109/TKDE.2022.3223155Recommender systems are playing a significant role in modern society to alleviate the information/choice overload problem, since Internet users may feel hard to identify the most favorite items or products from millions of candidates. Thanks to the recent ...
- research-articleAugust 2023
Local and global: temporal question answering via information fusion
- Yonghao Liu,
- Di Liang,
- Mengyu Li,
- Fausto Giunchiglia,
- Ximing Li,
- Sirui Wang,
- Wei Wu,
- Lan Huang,
- Xiaoyue Feng,
- Renchu Guan
IJCAI '23: Proceedings of the Thirty-Second International Joint Conference on Artificial IntelligenceArticle No.: 571, Pages 5141–5149https://doi.org/10.24963/ijcai.2023/571Many models that leverage knowledge graphs (KGs) have recently demonstrated remarkable success in question answering (QA) tasks. In the real world, many facts contained in KGs are time-constrained thus temporal KGQA has received increasing attention. ...
- research-articleAugust 2023
Finding hate speech with auxiliary emotion detection from self-training multi-label learning perspective
Information Fusion (INFU), Volume 96, Issue CPages 214–223https://doi.org/10.1016/j.inffus.2023.03.015AbstractHate Speech Detection (HSD) aims to identify whether a text contains hate speech content, which often refers to discrimination and is even associated with a hate crime. The mainstream methods jointly train the HSD problem with relevant ...
Highlights- Validating correlations between hate speech and specific negative emotions.
- ...
- research-articleJuly 2023
Weakly supervised regression with interval targets
ICML'23: Proceedings of the 40th International Conference on Machine LearningArticle No.: 215, Pages 5428–5448This paper investigates an interesting weakly supervised regression setting called regression with interval targets (RIT). Although some of the previous methods on relevant regression settings can be adapted to RIT, they are not statistically consistent, ...
- research-articleJune 2023
Adaptive prototype and consistency alignment for semi-supervised domain adaptation
Multimedia Tools and Applications (MTAA), Volume 83, Issue 3Pages 9307–9328https://doi.org/10.1007/s11042-023-15749-4AbstractUnsupervised Domain Adaptation (UDA) aims to transfer knowledge from a label-rich source domain to an unlabeled target domain whose data distributions are different. There is a more realistic scenario where a few target labels are available, ...
- research-articleJune 2023
S3 map: Semisupervised aspect-based sentiment analysis with masked aspect prediction
AbstractAspect-based sentiment analysis (ABSA) refers to a fine-grained task of detecting the sentiment polarities of sentences at the aspect level. To resolve this task, ABSA training samples must be annotated with aspect words and the ...
- research-articleFebruary 2023
Learning with partial labels from semi-supervised perspective
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 IntelligenceArticle No.: 974, Pages 8666–8674https://doi.org/10.1609/aaai.v37i7.26043Partial Label (PL) learning refers to the task of learning from the partially labeled data, where each training instance is ambiguously equipped with a set of candidate labels but only one is valid. Advances in the recent deep PL learning literature have ...