Networks
How Attentive are Graph Attention Networks?
目录概符号说明GATv2代码 Brody S., Alon U. and Yahav E. How attentive are graph attention networks? ICLR, 2022. 概 作者发现了 GAT 的 attention 并不能够抓住边的重要性, 于是提出了 GATv2 ......
Optimized Content Caching and User Association for Edge Computing in Densely Deployed Heterogeneous Networks论文阅读
目录Optimized Content Caching and User Association for Edge Computing in Densely Deployed Heterogeneous Networks1、问题背景贡献点：2、系统建模及问题公式化系统建模问题公式化联合内容缓存和用户 ......
Decoupling the Depth and Scope of Graph Neural Networks
目录概符号说明Shadow-GNN代码 Zeng H., Zhang M., Xia Y., Srivastava A., Malevich A., Kannan R., Prasanna V., Jin L. and Chen R. Decoupling the depth and scope o ......
study of 'Missing data imputation framework for bridge structural health monitoring based on slim generative adversarial networks'
the Stochastic Gradient Descent (SGD):为了提高鲁棒性，SGAIN框架的优化器采用了随机梯度下降（SGD） 一，SGAIN框架有两个重要目的：鉴别器D的目的是最大化正确预测M矩阵的概率；生成器的目的是最小化D预测M矩阵的概率。此外，利用反向传播算法对发生器和鉴别器 ......
SuperGlue: Learning Feature Matching with Graph Neural Networks论文笔记
SuperGlue: Learning Feature Matching with Graph Neural Networks 源码: github.com/magicleap/SuperGluePretrainedNetwork 背景： 主要解决图像中点之间的对应关系。 主要方法： 上图为该方法的 ......
Neural Networks投稿要求总结
自用，NN投稿要求，相关的部分的中文版翻译，原文链接：https://www.sciencedirect.com/journal/neural-networks/publish/guide-for-authors Neural Networks 投稿要求 介绍 国际神经网络学会、欧洲神经网络学会和日 ......
整理《DQNViz: A Visual Analytics Approach to Understand Deep Q-Networks》
DQNViz: A Visual Analytics Approach to Understand Deep Q-Networks 论文/强化学习可视化 摘要 打算研究深度强化学习方向，整理最近的一篇 2019 年的论文，作为总结思考！ 论文介绍 该论文是一篇 2019 年，有关基于可视化进行强化学 ......
Distilling Knowledge from Graph Convolutional Networks
目录概符号说明DistillGCNLocal Structure Preserving代码 Yang Y., Qiu J., Song M., Tao D. and Wang X. Distilling knowledge from graph convolutional networks. CVP ......
Graph Neural Networks with Adaptive Residual
目录概符号说明AirGNN代码 Liu X., Ding J., Jin W., Xu H., Ma Y., Liu Z. and Tang J. Graph neural networks with adaptive residual. NIPS, 2021. 概 基于 UGNN 框架的一个更加鲁 ......
Is Homophily a Necessity for Graph Neural Networks?
目录概 Ma Y., Liu X., Shah N. and Tang J. Is homophily a necessity for graph neural networks? ICLR, 2022. 概 探究 Homophily 假设 (即相互连接的结点相似) 对于 GCN 发挥效果是否是必须 ......
华为最高学术成果发表 —— 《Nature》正刊发表论文《Accurate medium-range global weather forecasting with 3D neural networks》
论文《Accurate medium-range global weather forecasting with 3D neural networks》的《Nature》地址： https://www.nature.com/articles/s41586-023-06185-3.pdf 论文的代码地 ......
GraphPrompt: Unifying Pre-Training and Downstream Tasks for Graph Neural Networks
目录概符号说明GraphPrompt代码 Liu Z., Yu X., Fang Y. and Zhang X. GraphPrompt: Unifying pre-training and downstream tasks for graph neural networks. WWW, 2023. ......
GPT-GNN: Generative Pre-Training of Graph Neural Networks
目录概符号说明GPT-GNN代码 Hu Z., Dong Y., Wang K., Chang K. and Sun Y. GPT-GNN: Generative pre-training of graph neural networks. KDD, 2020. 概 比较早的一篇图预训练模型. 符号 ......
【论文阅读】DeepAR Probabilistic forecasting with autoregressive recurrent networks
原始题目：DeepAR: Probabilistic forecasting with autoregressive recurrent networks 中文翻译：DeepAR:自回归递归网络的概率预测 发表时间：2020年07月 平台：International Journal of Forec ......
论文阅读（四）—— Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition
 ![image](https://img2023.cnblogs.com/blog/3279428/2... ......
Sequence to Sequence Learning with Neural Networks
Sequence to Sequence Learning with Neural Networks 关键词：LSTM，Seq2Seq 📜 研究主题 采用深度神经网络DNN 使用LSTM，并翻转输入句子顺序提升性能 ✨创新点： 更换seq2seq中RNN单元为LSTM，有提升对长句子训练速度的可能 ......
论文：Very deep convolutional networks for large-scale image recognition-VGG
论文名： Very deep convolutional networks for large-scale image recognition "用于大规模图像识别的深度卷积网络" 了解VGG模型 研究问题： 研究方法: 主要结论： 模型: 问题： 行文结构梳理： ......
Fi-GNN: Modeling Feature Interactions via Graph Neural Networks for CTR Prediction
目录概Fi-GNN代码 Li Z., Cui Z., Wu S., Zhang X. and Wang L. Fi-GNN: Modeling feature interactions via graph neural networks for ctr prediction. CIKM, 2019. ......
Convolutional Neural Networks（CNN）
数学基础 卷积 卷积这一概念从最原始来说属于一种数学的运算方法，两个数列进行卷积，是指将一个数列翻转后，从另一个数列最左侧开始滑动求和 来到计算机科学中，由于卷积核往往采用对称矩阵，所以翻转这一动作实际就可以忽略掉了。通过卷积核中数据的不同排列，实现提取出输入图片中的特定特征。 训练 + 预测 目前 ......
GNNExplainer: Generating Explanations for Graph Neural Networks论文阅读笔记
GNNExplainer: Generating Explanations for Graph Neural Networks论文阅读笔记 摘要 因为结合图结构和特征信息会导致复杂的模型，解释GNN的预测没有得到解决，所有提出了一个GNNExplainer，是第一个通用的，与模型无关的方法，可以 ......
AlexNet模型：ImageNet Classification with Deep Convolutional Neural Networks
文献名：ImageNet Classification with Deep Convolutional Neural Networks 创新点： 首次利用AlexNet神经网络，在ImageNet分类中以巨大的优势打败非神经网络算法 模型： ......
《ImageNet Classification with Deep Convolutional Neural Networks》阅读笔记
论文标题 《ImageNet Classification with Deep Convolutional Neural Networks》 ImageNet ：经典的划时代的数据集 Deep Convolutional：深度卷积在当时还处于比较少提及的地位，当时主导的是传统机器学习算法 作者 一作 ......
VERY DEEP CONVOLUTIONAL NETWORKS FOR LARGE
（VGG）VERY DEEP CONVOLUTIONAL NETWORKS FOR LARGE-SCALE IMAGE RECOGNITION 阅读笔记（22.10.05） 摘要：本文研究在大规模图像识别设置中卷积网络深度对其准确性的影响。主要贡献是对使用（3，3）卷积核的体系结构增加深度的网络进行 ......
VDSR-Accurate Image Super-Resolution Using Very Deep Convolutional Networks阅读笔记
Accurate Image Super-Resolution Using Very Deep Convolutional Networks（VDSR）阅读笔记（22.10.07）使用深度卷积网络的精确图像超分辨率 摘要：使用一个非常深的卷积神经网络，灵感来源于VGG-Net。本文发现，网络深度增加 ......
How Expressive are Graph Neural Networks in Recommendation
[TOC] > [Cai X., Xia L., Ren X. and Huang C. How expressive are graph neural networks in recommendation? CIKM, 2023.](http://arxiv.org/abs/2308.11127) ......
Proj CDeepFuzz Paper Reading: Testing Deep Neural Networks
## Abstract 本文:DeepCover Github: https://github.com/TrustAI/DeepCover Task: propose 4 novel test criteria to test DNNs Method: inspired by MC/DC cover ......
Proj CDeepFuzz Paper Reading: SparseProp: Efficient Sparse Backpropagation for Faster Training of Neural Networks
## Abstract 本文：SparseProp Github: https://github.com/IST-DASLab/sparseprop Task: a back-propagation algo for sparse training data, a fast vectorized i ......
Proj CDeepFuzz Paper Reading: Aries: Efficient Testing of Deep Neural Networks via Labeling-Free Accuracy Estimation
## Abstract 背景： 1. the de facto standard to assess the quality of DNNs in the industry is to check their performance (accuracy) on a collected set of ......
[KDD 2023] All in One- Multi-Task Prompting for Graph Neural Networks
# [KDD 2023] All in One- Multi-Task Prompting for Graph Neural Networks ## 总结 提出了个多任务prompt学习框架，扩展GNN的泛化能力： 1. 统一了NLP和图学习领域的prompt格式，包括prompt token、to ......