关于对比级联图学习框架的有效性:合成级联数据的力量
Daiki Suzuki1, Sho Tsugawa2, Keiichiro Tsukamoto3
1Graduate School of Engineering Information and Systems, University of Tsukuba, Tsukuba, Ibaraki, Japan.
PloS one
|October 16, 2023
概括
这项研究表明,预先训练的模型可以有效地跨越各种数据集进行级联流行预测. 合成数据可显著提高模型的准确性,当与训练的真实数据相结合时.
科学领域:
- 信息传播动态信息传播动态
- 网络科学 网络科学
- 机器学习用于社交网络分析
背景情况:
- 预测信息扩散级联对于各种应用至关重要.
- 之前的研究仅使用两个数据集,研究了在对比级联图学习框架中的模型可转移性.
- 目前的研究通过评估更广泛的数据集的可转移性来扩大这一点.
研究的目的:
- 综合评估预训练模型在对比级联图学习框架中的可转移性.
- 评估合成级联数据对预训和微调级联预测模型的有效性.
- 为了提高级联人气预测的准确性.
主要方法:
- 使用13个真实和6个合成级联数据集构建了预训练模型.
- 利用由独立的布和配置模型产生的合成布.
- 在真实级联数据集上微调模型,并使用平均平方对数误差评估预测准确性.
主要成果:
- 预先训练的模型在各种真实数据集 (不同领域,语言,平台,时间尺度) 中展示了可转移性.
- 合成级联数据在预训练中被证明是有效的,产生与真实数据相比的结果.
- 结合真实和合成数据进行微调,与单独使用真实数据相比,显著减少了预测误差.
结论:
- 预训练的模型在级联预测任务中表现出强大的可转移性.
- 合成数据是预训和微调级联预测模型的宝贵资源.
- 合成数据的使用提高了级联流行预测模型的准确性.
更多相关视频
08:05Measuring Statistical Learning Across Modalities and Domains in School-Aged Children Via an Online Platform and Neuroimaging Techniques
Published on: June 30, 2020
7.6K
07:12Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss
Published on: April 11, 2025
405
相关概念视频
Survival Tree
88
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
Building a Survival Tree
Constructing a...
Building a Survival Tree
Constructing a...
88
Cascaded Op Amps
643
Operational amplifiers (op-amps) are versatile electronic components that can be interconnected in a cascade - one after another in a linear sequence. This cascading is possible due to their infinite input resistance and zero output resistance, allowing them to maintain their input-output relationships even when connected in series.
In a cascaded system, each op-amp is referred to as a stage. The output of one stage drives the input of the subsequent stage. As the input signal passes through...
In a cascaded system, each op-amp is referred to as a stage. The output of one stage drives the input of the subsequent stage. As the input signal passes through...
643
Amplifying Signals via Enzymatic Cascade
8.5K
When a ligand binds to a cell-surface receptor, the receptor's intracellular domain changes shape, which may either activate its enzyme function or allow its binding to other molecules. The initial signal is amplified by most signal transduction pathways. This means that a single ligand molecule can activate multiple molecules of a downstream target. Proteins that relay a signal are most commonly phosphorylated at one or more sites, activating or inactivating the protein. Kinases catalyze...
8.5K
Rab Cascades
2.7K
Rab GTPases act in a regulated cascade during membrane fusion, helping the lipid bilayers mix. The Rab family of proteins are active when bound to GTP, and inactive when bound to GDP. Hence, they act as guanine nucleotide-dependent molecular switches. Rab-GTP recognizes and binds to long or short-range tethering proteins to capture the target vesicle. These tethers coordinate with SNAREs on the vesicle and the target membrane to assemble the trans SNARE complex that locks the mixing bilayers.
2.7K
Introduction to Learning
446
Learning is the process of acquiring knowledge or skills through practice or experience, leading to long-lasting behavioral changes. This acquisition occurs through interaction with the environment and requires practice or experience. For instance, mastering a skill such as surfing requires considerable practice and experience, highlighting the essential role of repeated interactions with the environment in learning.
In contrast to learned behaviors, unlearned behaviors such as crying, sexual...
In contrast to learned behaviors, unlearned behaviors such as crying, sexual...
446
Observational Learning
188
Albert Bandura's observational learning, also known as imitation or modeling, occurs when a person observes and imitates another's behavior. It is a quicker process than operant conditioning. A well-known example is the Bobo doll study, where children who saw an adult acting aggressively towards the doll were more likely to act aggressively when left alone, compared to those who observed a nonaggressive adult. Many psychologists view observational learning as a form of latent learning...
188
