Results 71 to 80 of about 12,623 (228)
Generating Compressed Counterfactual Hard Negative Samples for Graph Contrastive Learning
CAAI Transactions on Intelligence Technology, EarlyView.ABSTRACT Graph contrastive learning (GCL) relies on acquiring high‐quality positive and negative samples to learn the structural semantics of the input graph. Previous approaches typically sampled negative samples from the same training batch or an irrelevant external graph.
Haoran Yang +7 more
wiley +1 more source
Application Research of BiLSTM in Cross-Site Scripting Detection
Jisuanji kexue yu tansuo, 2020 At present, machine learning methods are used in the most traditional cross-site scripting (XSS) detection technologies, which have some defects, such as bad readability because of maliciously confused code, insufficient feature extraction and low ...
CHENG Qiqin, WAN Liang
doaj +1 more source
Proceedings of the 28th ACM International Conference on Information and Knowledge Management, 2019 The \em word2vec methodology such as Skip-gram and CBOW has seen significant interest in recent years because of its ability to model semantic notions of word similarity and distances in sentences. A related methodology, referred to as \em doc2vec is also able to embed sentences and paragraphs. These methodologies, however, lead to different embeddings
Suhang Wang +2 more
openaire +2 more sources
Accounting &Finance, EarlyView.ABSTRACT This study examines the negative effect of earnings pressure (EP) on corporate environmental, social, and governance (ESG) performance and explores governance mechanisms that can address this problem. Drawing on behavioural agency theory and incorporating insights from resource allocation theory and agency theory, this paper identifies the key
Sha Tang +2 more
wiley +1 more source
How do visual and conceptual factors predict the object content in typical scene drawings?
British Journal of Psychology, EarlyView.Abstract Imagine you draw a typical bedroom, your choice of objects is likely to depend on visual occurrence statistics (i.e. the objects present in previously encountered bedrooms) and semantic relations between objects and scenes (i.e. the semantic relationship between the bedroom and its constituent objects).
Gongting Wang +6 more
wiley +1 more source
Companion of the The Web Conference 2018 on The Web Conference 2018 - WWW '18, 2018 Clustering narrow-domain short texts, such as academic abstracts, is an extremely difficult clustering problem. Firstly, short texts lead to low frequency and sparseness of words, making clustering results highly unstable and inaccurate; Secondly, narrow domain leads to great overlapping of insignificant words and makes it hard to distinguish between ...
Changzhou Li +9 more
openaire +1 more source
Creativity and Innovation Management, Volume 34, Issue 4, Page 991-1012, December 2025.ABSTRACT Traditional techniques for evaluating creative outcomes are typically based on evaluations made by human experts. These methods suffer from challenges such as subjectivity, biases, limited availability, ‘crowding’, and high transaction costs. We propose that large language models (LLMs) can be used to overcome these shortcomings.
Theresa Kranzle, Katelyn Sharratt
wiley +1 more source
Computer Graphics Forum, EarlyView.Abstract Network visualization has traditionally relied on heuristic metrics, such as stress, under the assumption that optimizing them leads to aesthetic and informative layouts. However, no single metric consistently produces the most effective results.
X. Li, P. Zhang, X. Wang, H. Shen, Y. Hu
wiley +1 more source