基于GNN的协作过,具有属性融合和广泛关注
MingXue Liu1, Min Wang1,2, Baolei Li1,2
1School of Mathematics and Computer Science, Gannan Normal University, Ganzhou, China.
PeerJ. Computer science
|March 10, 2025
概括
本研究介绍了GNN-A2,一种用于协作过 (CF) 的新型图形神经网络 (GNN) 方法,通过更好地利用属性信息和更高阶交互来提高推准确性. 在GNN-A2模型显著改善正常化折扣累积收益 (NDCG@10) 超过现有的最先进的方法.
科学领域:
- 人工智能的人工智能
- 机器学习 机器学习
- 数据挖掘 数据挖掘
背景情况:
- 协作过 (CF) 对推系统至关重要.
- 传统的CF方法与非线性和更高阶的特征相互作用作斗争.
- 图形神经网络 (GNN) 是有前途的,但在属性聚合和利用高阶信息方面存在局限性.
研究的目的:
- 提出一种新的基于GNN的CF模型,GNN-A2,以解决现有的GNNCF方法的局限性.
- 通过有效区分和聚合属性相互作用来提高推性能.
- 为了利用更高层次的相互作用信息进行更准确的预测.
主要方法:
- 开发了GNN-A2,一种基于GNN的CF方法,结合了属性融合和广泛关注.
- 实现了一个内在交互模块与自我注意.
- 设计了一个具有属性融合的交叉交互模块和一个广泛的注意力交叉模块.
主要成果:
- 在曲线下的面积 (AUC) 中,GNN-A2表现相似.
- 在三个基准数据集 (MovieLens 1M,Book-crossing,Taobao) 中,在第10位 (NDCG@10) 实现了最佳的规范化折扣累积收益.
- 在NDCG@10.中,超越最先进的 (SOTA) 模型的性能高达2.14%.
结论:
- GNN-A2有效地以不同的方式处理内部和交叉相互作用,提取更高阶信息以改善预测.
- 拟议的模型为基于GNN的协作过提供了显著的进步.
- 实验结果验证了GNN-A2在基准数据集上的优越性.
相关概念视频
01:24Tagging and Fusion Proteins
6.6K
Proteins are involved in several cellular processes and biochemical reactions. Analyzing a specific protein of interest requires it to be isolated from the other proteins in the cell. This is achieved by overexpressing the specific gene in a suitable host to produce large quantities of the target protein. A tag or label is recombined with the gene to produce a fusion protein containing the target protein and the tag. The tags on these fusion proteins can then be used for easy detection and...
6.6K
01:25Active Filters
707
Active filters are electronic circuits that use operational amplifiers (op-amps), resistors, and capacitors to filter out unwanted frequency components from a signal. A first-order low-pass active filter is designed to pass signals with a frequency lower than a certain cutoff frequency and attenuate frequencies higher than that cutoff frequency. The transfer function for a first-order low-pass active filter is:
707
00:53Filtration
747
Filtration is a physical separation process that involves passing a suspension through a porous medium to separate solids from fluids. During filtration, solids collect on the porous medium while liquids, also collectively known as the filtrate, pass through. The filtration medium is selected based on the filtration purpose, quantity, and nature of the precipitate. The general criteria for a suitable filtering medium are that it is inert, mechanically strong, nonabsorbent toward dissolved...
747
01:41Affinity and Avidity
35.7K
Overview
35.7K
01:27Passive Filters
446
Passive filters are utilized to shape the frequency spectrum of signals across a diverse array of applications. These filters, using only passive elements like resistors (R), inductors (L), and capacitors (C), are capable of selectively allowing or blocking certain frequency ranges without the need for external power sources.
Low-Pass Filters
Low-pass filters are designed to transmit signals with frequencies lower than the cutoff frequency, ωc, and attenuate those above it. The cutoff...
Low-Pass Filters
Low-pass filters are designed to transmit signals with frequencies lower than the cutoff frequency, ωc, and attenuate those above it. The cutoff...
446
01:29Aggregates Classification
298
Aggregate classification is generally based on its size, petrographic characteristics, weight, and source. Size classification ranges from coarse to fine aggregates, defined by the size of the particles. Coarse aggregates are particles that do not pass through ASTM sieve No. 4, and aggregates that pass through the sieve are fine aggregates.
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...
298