graph recommendation augmentations contrastive
D. Fish Graph
D. Fish Graph You are given a simple undirected graph with $n$ nodes and $m$ edges. Note that the graph is not necessarily connected. The nodes are la ......
Controllable Guarantees for Fair Outcomes via Contrastive Information Estimation
Gupta U., Ferber A. M., Dilkina B. and Steeg G. V. Controllable guarantees for fair outcomes via contrastive information estimation. AAAI, 2021. 概 本文提 ......
Graph Convolutional Networks with EigenPooling
Ma Y., Wang S., Aggarwal C. C. and Tang J. Graph convolutional networks with eigenpooling. KDD, 2019. 概 本文提出了一种新的框架, 在前向的过程中, 可以逐步将相似的 nodes 和他们的特征聚合在 ......
Handling Information Loss of Graph Neural Networks for Session-based Recommendation
Chen T. and Wong R. C. Handling information loss of graph neural networks for session-based recommendation. KDD, 2020. 概 作者发现图用在 Session 推荐中存在: lossy ......
B. Greg and Graph
题目 B. Greg and Graph 题意 输入 n(1≤n≤500) 表示 n 个点的有向完全图,然后输入 n*n 的邻接矩阵 a,其中 a[i][j] 表示 i 到 j 的边权,范围 [1,1e5](特例是 a[i][i]=0)。 图的节点编号从 1 开始。 然后输入 1~n 的排列,表示我 ......
Codeforces Round 847 (Div. 3) G.Tokens on Graph (构造)
传送门 题目大意 ** 给定一个无向图,我们定义图中有四种点,一种是黑色的点表示终点,并且黑色的点始终是1号点,一种是红色的点,一种是灰色的点,最后一种就是没有颜色的点。** ** 游戏规则:我们必须移动任意一个灰色的点到相邻的点上,如果灰色的点移动到了红色的点上,那么我们可以移动其他灰色的点继续上 ......
解决 c3p0报错 Establishing SSL connection without server's identity verification is not recommended
解决 c3p0报错 Establishing SSL connection without server's identity verification is not recommended ?useSSL=false <c3p0-config> <default-config> <property ......
2022AAAI_Semantically Contrastive Learning for Low-light Image Enhancement(SCL_LLE)
1. motivation 利用语义对比学习 2. network (1) 输入的是低光图像首先经过图像增强的网络(Zero-DCE), 再将它传入语义分割网络中 (2)语义分割网络用的是DeepLabv3+ ......
spectral-graph-theory-in-GCN
GCN 中的谱图理论笔记 Datetime: 2023-04-26T09:36+08:00 Categories: MachineLearning Tags: GNN 写毕设,发现自己没法绕过第一代 GCN 的谱图变换原理 我知道啥是傅里叶变化,但是我感觉不到那种新奇,或许这就是无法感觉到数学的美吧 ......
Invariant and Equivariant Graph Networks
Maron H., Ben-Hamu H., Shamir N. and Lipman Y. Invariant and equivariant graph networks. ICLR, 2019. 概 有些时候, 我们希望网络具有: 不变性 (Invariant): $$ f(PX) = f(X ......
图(Graph)与图论
听到图这个字,很多人会联想到图片、折线图、设计图等传统的图,今天要聊的图(Graph)是一种基本研究对象,用于表示实体与实体之间的关系。 先说结论: 图论:是组合数学分支,是主要研究图的学问,起源于柯尼斯堡七桥问题。 图(数学):是用于表示物体与物体之间存在某种关系的结构。数学抽象后的“物体”称作节 ......
题解:【CF235D】Graph Game
题目链接 根据期望的线性性,一次操作使得接下来要递归处理 $|G|$ 个点,将这些贡献分摊到 $|G|$ 个点上,这样我们接下来只需要计算概率。 首先考虑如果是树怎么做。操作等价于随机一个排列,顺次删掉排列中的点,并求出删掉当前点之前其所处的连通块的大小。记当前 $x$ 为点分治中心,点对 $(x, ......
Graph Travarsal All In One
Graph traversal All In One 图遍历 js / ts demos --> (🐞 反爬虫测试!打击盗版⚠️)如果你看到这个信息, 说明这是一篇剽窃的文章,请访问 https://www.cnblogs.com/xgqfrms/ 查看原创文章! refs ©xgqfrms 20 ......
Layer-Dependent Importance Sampling for Training Deep and Large Graph Convolutional Networks
Zou D., Hu Z., Wang Y., Jiang S., Sun Y. and Gu Q. Layer-dependent importance sampling for training deep and large graph convolutional networks. NIPS, ......
Codeforces Round 550 (Div. 3) F. Graph Without Long Directed Paths(dfs/染色)
https://codeforces.com/contest/1144/problem/F 题目大意: 给定n个点,m条边; 每一条边都连接了两个点。 现在需要我们染色,要求是做到所有有向图不包含长度为2或者更长的路径。 input 6 5 1 5 2 1 1 4 3 1 6 1 output YE ......
Heterogeneous Graph Attention Network
Wang X., Ji H., Shi C., Wang B., Cui P., Yu P. and Ye Y. Heterogeneous graph attention network. WWW, 2019. 概 Attention + 异构图. 符号说明 $\mathcal{G} = (\ma ......
Heterogeneous Deep Graph Infomax
Ren Y., Liu B., Huang C., Dai P., Bo L. and Zhang J. Heterogeneous deep graph infomax. arXiv preprint arXiv:1911.08538, 2019. 概 本文介绍了异构图的一种无监督学习方法. 这里 ......
AtCoder Regular Contest 105 E Keep Graph Disconnected
洛谷传送门 AtCoder 传送门 显然终止态是只剩两个连通块,一个包含 $1$ 另一个包含 $n$,并且两个连通块内的边数均为 $\frac{sz(sz-1)}{2}$。 如果只在连通块内连边,那么能连的边的总数是 $\frac{n(n-1)}{2} - \sum\limits_{i=1}^{cn ......
迁移学习(CLDA)《CLDA: Contrastive Learning for Semi-Supervised Domain Adaptation》
论文信息 论文标题:CLDA: Contrastive Learning for Semi-Supervised Domain Adaptation论文作者:Ankit Singh论文来源:NeurIPS 2021论文地址:download 论文代码:download视屏讲解:click 1 简介 ......
Multi-View Attribute Graph Convolution Networks for Clustering
论文阅读04-Multi-View Attribute Graph Convolution Networks for Clustering:MAGCN 论文信息 论文地址:Multi-View Attribute Graph Convolution Networks for Clustering | ......
Deep graph clustering with enhanced feature representations for community detection
论文阅读03-EFR-DGC:Enhanced Feature Representations for Deep Graph Clustering 论文信息 论文地址:Deep graph clustering with enhanced feature representations for co ......
Attributed Graph Clustering |A Deep Attentional Embedding Approach
论文阅读01-Attributed Graph Clustering: A Deep Attentional Embedding Approach 1. 创新点idea Two-step的图嵌入方法不是目标导向的,聚类效果不好,提出一种基于目标导向的属性图聚类框架。 所谓目标导向,就是说特征提取和聚 ......
FastGCN Fast Learning with Graph Convolutional Networks via Importance Sampling
Chen J., Ma T. and Xiao C. FastGCN: fast learning with graph convolutional networks via importance sampling. ICLR, 2018. 概 一般的 GCN 每层通常需要经过所有的结点的 prop ......
Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning
Li Q., Han Z. and Wu X. Deeper insights into graph convolutional networks for semi-supervised learning. AAAI, 2018. 概 本文分析了 GCN 的实际上就是一种 Smoothing, 但是 ......
Stochastic Training of Graph Convolutional Networks with Variance Reduction
Chen J., Zhu J. and Song L. Stochastic training of graph convolutional networks with variance reduction. ICML, 2018. 概 我们都知道, GCN 虽然形式简单, 但是对于结点个数非常多的 ......
Shortest Cycle in a Graph
Shortest Cycle in a Graph There is a bi-directional graph with n vertices, where each vertex is labeled from 0 to n - 1. The edges in the graph are re ......
【Azure Developer】使用 Microsoft Graph API 获取 AAD User 操作示例
问题描述 查看官方文档“ Get a user ” , 产生了一个操作示例的想法,在中国区Azure环境中,演示如何获取AAD User信息。 问题解答 使用Microsoft Graph API,演示如何获取AAD User信息,因参考文档是针对Global Azure,所以文档种的URL为: / ......
Graphs with Python: Overview and Best Libraries
Graphs with Python: Overview and Best Libraries Graph analysis, interactive visualizations, and graph machine learning A graph is a relatively old mat ......
DiffuRec: A Diffusion Model for Sequential Recommendation
Li Z., Sun A. and Li C. DiffuRec: A diffusion model for sequential recommendation. arXiv preprint arXiv:2304.00686, 2023. 概 扩散模型用于序列推荐, 性能提升很大. DiffuR ......
异常检测 | 迁移学习《Anomaly Detection in IR Images of PV Modules using Supervised Contrastive Learning》
论文信息 论文标题:Anomaly Detection in IR Images of PV Modules using Supervised Contrastive Learning论文作者:Abhay Rawat, Isha Dua, Saurav Gupta, Rahul Tallamraju ......