526互联

graph recommendation augmentations contrastive

Exploiting Positional Information for Session-based Recommendation

[TOC] > [Qiu R., Huang Z., Chen T. and Yin H. Exploiting positional information for session-based recommendation. ACM Transactions on Information Syst ......
Recommendation Session-based Information Exploiting Positional

Contrastive Learning for Representation Degeneration Problem in Sequential Recommendation

[TOC] > [Qiu R., Huang Z., Ying H. and Wang Z. Contrastive learning for representation degeneration problem in sequential recommendation. WSDM, 2022.] ......
Representation Recommendation Degeneration Contrastive Sequential

Self-Supervised Hypergraph Convolutional Networks for Session-based Recommendation

[TOC] > [Xia X., Yin H., Yu J., Wang Q., Cui L and Zhang X. Self-supervised hypergraph convolutional networks for session-based recommendation. AAAI, ......
Self-Supervised Recommendation Convolutional Session-based Hypergraph

Self-Supervised Graph Co-Training for Session-based Recommendation

[TOC] > [Xia X., Yin H., Yu J., Shao Y. and Cui L. Self-supervised graph co-training for session-based recommendation. CIKM, 2021.](http://arxiv.org/a ......
Self-Supervised Recommendation Session-based Co-Training Supervised

Global Context Enhanced Graph Neural Networks for Session-based Recommendation

[TOC] > [Wang Z., Wei W., Cong G., Li X., Mao X. and Qiu M. Global context enhanced graph neural networks for session-based recommendation. SIGIR, 202 ......
Recommendation Session-based Enhanced Networks Context

CF506D - Mr. Kitayuta's Colorful Graph

本质不同的算法主要有两种：对子图大小根号分治和类启发式均摊。此外还有很多实现上的差别。 #### 对子图大小根号分治 在线做法： 我们发现，把每个颜色的边和它们的顶点取出为一个子图，所有子图大小的和是 $O(n)$ 级别的。那么我们就可以根号分治。 首先，要预处理每个颜色子图下的连通块。可以用并查集 ......
Kitayuta Colorful Graph 506D 506

Neural Attentive Session-based Recommendation

[TOC] >[ Li J., Ren P., Chen Z., Ren Z., Lian T. and Ma J. Neural attentive session-based recommendation. CIKM, 2017.](http://arxiv.org/abs/1711.04725 ......
Recommendation Session-based Attentive Session Neural

转载-奇小葩-深入ftrace function graph原理

原文链接：https://blog.csdn.net/u012489236/article/details/127838701 学习完了ftrace的function的基本功能，其作用主要是用来跟踪特定内核函数调用的频次，对于内核，特别是初学者，对于函数的调用关系不清晰，并且内核中有很多函数指针，会 ......
function 原理 ftrace graph

AtCoder Regular Contest 161 E Not Dyed by Majority (Cubic Graph)

[洛谷传送门](https://www.luogu.com.cn/problem/AT_arc161_e "洛谷传送门") [AtCoder 传送门](https://atcoder.jp/contests/arc161/tasks/arc161_e "AtCoder 传送门") 给构造题提供了一种 ......
Majority AtCoder Regular Contest Cubic

Memory Priority Model for Session-based Recommendation

[TOC] > [Liu Q., Zeng Y., Mokhosi R. and Zhang H. STAMP: Short-term attention/memory priority model for session-based recommendation. KDD, 2018.](http ......
Recommendation Session-based Priority Session Memory

The Open Graph protocol(开放图谱协议)的介绍及应用

### 介绍 `Open Graph 协议`使任何网页都可以成为社交中的丰富对象。例如，用于 `Facebook` 以允许任何网页具有与 `Facebook `上任何其他对象相同的功能。 以下是把链接分享到`钉钉`，钉钉识别后显示的效果： ![](https://oss.milovetingting ......
图谱 protocol Graph Open The

Permutation Invariant Graph Generation via Score-Based Generative Modeling

[TOC] > [Niu C., Song Y., Song J., Zhao S., Grover A. and Ermon S. Permutation invariant graph generation via score-based generative modeling. AISTATS ......
Permutation Score-Based Generation Generative Invariant

Efficient Graph Generation with Graph Recurrent Attention Networks

[TOC] > [Liao R., Li Y., Song Y., Wang S., Nash C., Hamilton W. L., Duvenaud D., Urtasun R. and Zemel R. NIPS, 2019.](http://arxiv.org/abs/1910.00760) ......
Graph Generation Efficient Attention Recurrent

B. Complete The Graph

B. Complete The Graph ZS the Coder has drawn an undirected graph of $n$ vertices numbered from $0$ to $n - 1$ and $m$ edges between them. Each edge of ......
Complete Graph The

Graph Normalizing Flows

[TOC] > [Liu J., Kumar A., Ba J., Kiros J. and Swersky K. Graph normalizing flows. NIPS, 2019.](http://arxiv.org/abs/1905.13177) ## 概 基于 [flows](https ......
Normalizing Graph Flows

Graph Embedding：LINE算法

背景 如上图所示，结点6和7是相邻结点，他们应该是相似结点，结点5和6虽然不是相邻结点，但是它们有共同的相邻的结点，因此它们也应该是相似结点。 基于词观察，LINE算法提出了一阶相似性算法和二阶相似性算法 First-order 我们首先如如下公式来计算结点i和j的联合概率分布： 其中ui，uj​分 ......
算法 Embedding Graph LINE

Test Time Augmentation

# 1.概念 ## 1.1 数据增强 Data Augmentation，训练过程中经常使用数据增强技术 > 大型数据集是成功应用深度神经网络的先决条件。 图像增广在对训练图像进行一系列的随机变化之后，生成相似但不同的训练样本，从而**扩大了训练集的规模**。 此外，应用图像增广的原因是，**随机改 ......
Augmentation Test Time

Paper Reading: forgeNet a graph deep neural network model using tree-based ensemble classifiers for feature graph construction

[toc] Paper Reading 是从个人角度进行的一些总结分享，受到个人关注点的侧重和实力所限，可能有理解不到位的地方。具体的细节还需要以原文的内容为准，博客中的图表若未另外说明则均来自原文。 | 论文概况 | 详细 | | | | | 标题 | 《forgeNet: a graph dee ......
graph construction classifiers tree-based forgeNet

经典的Graph Embedding方法：DeepWalk 和 Node2vec

DeepWalk Deep Walk，它是 2014 年由美国石溪大学的研究者提出的。它的主要思想是在由物品组成的图结构上进行随机游走，产生大量物品序列，然后将这些物品序列作为训练样本输入 Word2vec 进行训练，最终得到物品的 Embedding Node2vec 2016 年，斯坦福大学的研 ......
Embedding DeepWalk Node2vec 方法 经典

Combining Label Propagation and Simple Models Out-performs Graph Neural Networks

[TOC] > [Huang Q., He H., Singh A., Lim S. and Benson A. R. Combining label propagation and simple models out-performs graph neural networks. ICLR, 20 ......
Out-performs Propagation Combining Networks performs

POJ1737 Connected Graph ( n点无向连通图计数

题意说明:求 $n$ 个点的无向连通图个数 据说已经非常典了,但是我太菜了不会组合数学,最近补档时看到这道题,决定记录下来理理思路 ![image](https://img2023.cnblogs.com/blog/3146663/202305/3146663-20230520234501796-1 ......
Connected Graph 1737 POJ

基于Graph-Cut算法的彩色图像深度信息提取matlab仿真

1.算法仿真效果 matlab2022a仿真结果如下： 2.算法涉及理论知识概要 Graph cuts是一种十分有用和流行的能量优化算法，在图像处理领域普遍应用于前后背景分割（Image segmentation）、立体视觉（stereo vision）、抠图（Image matting）等，目前在 ......
算法 Graph-Cut 深度 图像 彩色

Peripheral Instance Augmentation for End-to-End

Peripheral Instance Augmentation for End-to-End Anomaly Detection Using Weighted Adversarial Learning abstract 对边缘样本的实例学习不足，可能会导致较高的假阳性 提出方法用少量样本来指导对抗 ......
Augmentation Peripheral End-to-End End Instance

【图像数据增强】Image Data Augmentation for Deep Learning: A Survey

| 原始题目 | Image Data Augmentation for Deep Learning: A Survey | | | | | 中文名称 | 深度学习的图像数据增强:综述 | | 发表时间 | 2022年4月19日 | | 平台 | arXiv | | 来源 | 南京大学 | | 文章 ......
Augmentation Learning 图像 数据 Survey

Do Transformers Really Perform Badly for Graph Representation

Ying C., Cai T., Luo S., Zheng S., Ke D., Shen Y. and Liu T. Do transformers really perform badly for graph representation? NIPS, 2021. 概 本文提出了一种基于图的 ......
Representation Transformers Perform Really Badly

Understanding Structural Vulnerability in Graph Convolutional Networks

Chen L., Li J., Peng Q., Liu Y., Zheng Z. and Yang C. Understanding structural vulnerability in graph convolutional networks. IJCAI, 2021. 概 mean 是在 G ......
Understanding Convolutional Vulnerability Structural Networks

Personalized Top-N Sequential Recommendation via Convolutional Sequence Embedding

Tang J. and Wang K. Personalized top-n sequential recommendation via convolutional sequence embedding. WSDM, 2018. 概 序列推荐的经典之作, 将卷积用在序列推荐之上. 符号说明 $\ma ......
Recommendation Convolutional Personalized Sequential Embedding

MBN:Mutual Boost Network for Attributed Graph Clustering

论文阅读07-MBN:Mutual Boost Network for Attributed Graph Clustering 论文信息 论文地址：https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4195979 代码地址：https://git ......
Attributed Clustering Network Mutual Boost

论文解读《Mixup for Node and Graph Classification》

论文信息 论文标题：Mixup for Node and Graph Classification论文作者：Yiwei Wang、Wei Wang论文来源：WWW 2021论文地址：download 论文代码：download视屏讲解：click 1 介绍 ......
Classification 论文 Mixup Graph Node

论文解读（ID-MixGCL）《ID-MixGCL: Identity Mixup for Graph Contrastive Learning》

论文信息 论文标题：ID-MixGCL: Identity Mixup for Graph Contrastive Learning论文作者：Gehang Zhang.....论文来源：2023 aRxiv论文地址：download 论文代码：download视屏讲解：click 介绍 ......
ID-MixGCL MixGCL Contrastive Identity Learning
共360篇  :9/12页 首页上一页9下一页尾页