This article is about 10,000 words long, and it is recommended to read for over 10 minutes. This article introduces graph FMs and provides examples of their use. Foundation models in language, vision, and audio have become one of the main research topics in machine learning for 2024, while FMs targeting graph-structured data are somewhat … Read more
This article is approximately 9000 words long and is recommended for a reading time of over 10 minutes. This article analyzes the reliability risks of GNNs from a causal perspective and introduces six sets of techniques to gain deeper insights into potential causal mechanisms and achieve reliability. 1 Introduction This article reviews the latest advancements … Read more
Author: yyHaker Source: https://zhuanlan.zhihu.com/p/136521625 This article is about 5900 words long and is recommended to be read in 10 minutes. This article will provide a simple summary from a more intuitive perspective of the currently popular classic GNN networks, including GCN, GraphSAGE, GAT, GAE, and graph pooling strategies such as DiffPool. In recent years, the … Read more
Single-cell RNA sequencing (scRNA-seq) technology enables gene expression detection across the transcriptome within individual cells, which can be used to study somatic clonal structures and characterize cellular heterogeneity in complex diseases. However, the data from scRNA-seq analysis are characterized by complexity, uncertain distributions, large data volumes, and high missing rates, making scRNA-seq analysis for biological … Read more
Source: ZHUAN ZHI This article serves as a tutorial and is recommended for a 5-minute read. This tutorial's practical section will be based on TF-GNN, a library for handling graph-structured data in TensorFlow. Graphs are universal data structures that can represent information from various domains (social, biomedical, online transactions, etc.). Graph Neural Networks (GNNs) are … Read more
Source: Algorithm Advancement This article is approximately 4200 words long and is recommended for an 8-minute read. This article will introduce key parts of the "Graph Attention Networks" and implement the concepts proposed in the paper using PyTorch. Graph Neural Networks (GNN) are a powerful class of neural networks that operate on graph-structured data. They … Read more
Convolutional Neural Networks are a type of feedforward neural network that includes convolutional operations and has a deep structure, representing one of the key algorithms in deep learning. This article aims to introduce the basic concepts and structures of CNN, as well as the fundamental ideas behind CNN architecture design. This article is packed with … Read more
Follow the official account “ML_NLP“ Set as “Starred“, essential resources delivered first-hand! Looking back at the phrase from 2017, “Attention is all you need”, it truly was a prophetic statement. The Transformer model started with machine translation in natural language processing, gradually influencing the field (I was still using LSTM in my graduation thesis in … Read more
Introduction Graph Neural Networks (GNN) — a dark horse among various neural networks. It is widely applicable across various fields, including recommendation systems, Google Maps traffic prediction, drug discovery, protein discovery, and more. To explore the development and real-world applications of graph neural networks in algorithmic neural solving, the Intelligence Club, in collaboration with Associate … Read more
Source: AI Youdao Extreme Market Platform This article is approximately 5900 words long and is recommended for a reading time of 10 minutes. This article will provide a brief summary from a more intuitive perspective of the currently classic and popular GNN networks, including GCN, GraphSAGE, GAT, GAE, and graph pooling strategies like DiffPool, etc. … Read more