Fresh picks from ArXiv
This week on ArXiv: 1000-layer GNN, solutions to OGB challenge, and theory behind GNN explanations 🤔

If I forgot to mention your paper, please shoot me a message and I will update the post.


Deep GNNs
* Training Graph Neural Networks with 1000 Layers ICML 2021
* Very Deep Graph Neural Networks Via Noise Regularisation with Petar Veličković, Peter Battaglia

Heterophily
* Improving Robustness of Graph Neural Networks with Heterophily-Inspired Designs with Danai Koutra

Knowledge graphs
* Query Embedding on Hyper-relational Knowledge Graphs with Mikhail Galkin

OGB-challenge
* Fast Quantum Property Prediction via Deeper 2D and 3D Graph Networks
* First Place Solution of KDD Cup 2021 & OGB Large-Scale Challenge Graph Prediction Track

Theory
* Towards a Rigorous Theoretical Analysis and Evaluation of GNN Explanations with Marinka Zitnik
* A unifying point of view on expressive power of GNNs

GNNs
* Stability of Graph Convolutional Neural Networks to Stochastic Perturbations with Alejandro Ribeiro
* TD-GEN: Graph Generation With Tree Decomposition
* Unsupervised Resource Allocation with Graph Neural Networks
* Equivariance-bridged SO(2)-Invariant Representation Learning using Graph Convolutional Network
* GemNet: Universal Directional Graph Neural Networks for Molecules with Stephan Günnemann
* Optimizing Graph Transformer Networks with Graph-based Techniques

Survey
* Systematic comparison of graph embedding methods in practical tasks
* Evaluating Modules in Graph Contrastive Learning
* A Survey on Mining and Analysis of Uncertain Graphs

@Machine_learn

Facebook's Reverse engineering generative models from a single deepfake image

Github: https://github.com/vishal3477/Reverse_Engineering_GMs

Paper: https://arxiv.org/abs/2106.07873

Facebook's blog: https://ai.facebook.com/blog/reverse-engineering-generative-model-from-a-single-deepfake-image/

Dataset: https://drive.google.com/drive/folders/1ZKQ3t7_Hip9DO6uwljZL4rYAn5viSRhu?usp=sharing

@Machine_learn

Amazon, Berkeley release dataset of product images and metadata.
Dataset includes multiple images of 147,702 products, including 360° rotations and 3-D models for thousands of them.


https://www.amazon.science/blog/amazon-berkeley-release-dataset-of-product-images-and-metadata

@Machine_learn

Breast Cancer Wisconsin (Diagnostic) Data Set

Predict whether the cancer is benign or malignant

Here is link of dataset: Link

🔷 Number of instances: 569
🔷 Number of attributes: 32 (ID, diagnosis, 30 real-valued input features)
🔷 Ten real-valued features are computed for each cell nucleus:

a) radius (mean of distances from center to points on the perimeter)
b) texture (standard deviation of gray-scale values)
c) perimeter
d) area
e) smoothness (local variation in radius lengths)
f) compactness (perimeter^2 / area - 1.0)
g) concavity (severity of concave portions of the contour)
h) concave points (number of concave portions of the contour)
i) symmetry
j) fractal dimension ("coastline approximation" - 1)


#dataset
@Machine_learn

R and Python for oceanographers

⬇️ Book

@Machine_learn

Self-Supervised Learning with Swin Transformers

Github: https://github.com/SwinTransformer/Transformer-SSL

Paper: https://arxiv.org/abs/2105.04553v2

@Machine_learn

SMURF: Self-Teaching Multi-Frame Unsupervised RAFT with Full-Image Warping

Paper:
https://arxiv.org/pdf/2105.07014.pdf

Video:
https://www.youtube.com/watch?v=W7NCbfZp6QE

Code:
https://github.com/google-research/google-research/tree/master/smurf

@Machine_learn

GIRAFFE: A Closer Look at the Code for CVPR 2021’s Best Paper

[Paper] http://www.cvlibs.net/publications/Niemeyer2021CVPR.pdf

[Source] https://github.com/autonomousvision/giraffe

[Blog] https://autonomousvision.github.io/giraffe/

[Interactive slides] https://m-niemeyer.github.io/slides/#/4

[Collected] https://m-niemeyer.github.io/project-pages/giraffe/index.html

@Machine_learn

Jason Brownlee
Master Machine Learning Algorithms Discover How They Work and Implement Them From Scratch
#Ml #book
@Machine_learn

EL-Attention: Memory Efficient Lossless Attention for Generation

Github: https://github.com/microsoft/fastseq

Paper: https://arxiv.org/abs/2105.04779v1

@Machine_learn

Deep Learning Dataset For Passage and Document Retrieval

Github: https://github.com/grill-lab/DL-Hard

Paper: https://arxiv.org/abs/2105.07975v1

@Machine_learn

Cartoon-StyleGan2 🙃 : Fine-tuning StyleGAN2 for Cartoon Face Generation

Github: https://github.com/happy-jihye/Cartoon-StyleGan2

Paper: https://arxiv.org/abs/2106.12445

Colab: https://colab.research.google.com/github/happy-jihye/Cartoon-StyleGan2/blob/main/Cartoon_StyleGAN2.ipynb

@Machine_learn

Neural Networks and Introduction to Deep Learning
#RNN #DL
@Machine_learn

🌠 Deepmind's Generally capable agents emerge from open-ended play

Blog : https://deepmind.com/blog/article/generally-capable-agents-emerge-from-open-ended-play

Paper: https://deepmind.com/research/publications/open-ended-learning-leads-to-generally-capable-agents

DeepMind Research: https://github.com/deepmind/deepmind-research

Video: https://www.youtube.com/watch?v=lTmL7jwFfdw&ab_channel=DeepMind

@Machine_learn

A Dataset for Studying Gender Bias in Translation


http://ai.googleblog.com/2021/06/a-dataset-for-studying-gender-bias-in.html

@Machine_learn

Deep Learning based Vehicle Detection in Aerial Imagery
Sommer, Lars Wilko #2021 #book #DL @Mchine_learn

Deep Learning
with Python
Learn Best Practices of
Deep Learning Models
with PyTorch Ketkar, Nikhil ; Moolayil, Jojo #2021 #DL #Book #PyTorch @Machine_learn

با عرض سلام ما پكيج ٣٦ پروژه عملي با يادگيري عميق همراه با داكيومنت فارسي را براي دوستاني كه مي خواهند در اين حوزه به صورت عملي كار كنند تهيه كرديم سرفصل هاي اين پكيج به ترتيب زير مي باشند:


1-Deep Learning Basic
-01_Introduction
--01_How_TensorFlow_Works
--02_Creating_and_Using_Tensors
--03_Implementing_Activation_Functions
-02_TensorFlow_Way
--01_Operations_as_a_Computational_Graph
--02_Implementing_Loss_Functions
--03_Implementing_Back_Propagation
--04_Working_with_Batch_and_Stochastic_Training
--05_Evaluating_Models
-03_Linear_Regression
--linear regression
--Logistic Regression
-04_Neural_Networks
--01_Introduction
--02_Single_Hidden_Layer_Network
--03_Using_Multiple_Layers
-05_Convolutional_Neural_Networks
--Convolution Neural Networks
--Convolutional Neural Networks Tensorflow
--TFRecord For Deep learning Models
-06_Recurrent_Neural_Networks
--Recurrent Neural Networks (RNN)
2-Classification apparel
-Classification apparel double capsule
-Classification apparel double cnn
3-ALZHEIMERS USING CNN(ResNet)
4-Fake News (Covid-19 dataset)
-Multi-channel
-3DCNN model
-Base line+ Char CNN
-Fake News Covid CapsuleNet
5-3DCNN Fake News
6-recommender systems
-GRU+LSTM MovieLens
7-Multi-Domain Sentiment Analysis
-Dranziera CapsuleNet
-Dranziera CNN Multi-channel
-Dranziera LSTM
8-Persian Multi-Domain SA
-Bi-GRU Capsule Net
-Multi-CNN
9-Recommendation system
-Factorization Recommender, Ranking Factorization Recommender, Item Similarity Recommender (turicreate)
-SVD, SVD++, NMF, Slope One, k-NN, Centered k-NN, k-NN Baseline, Co-Clustering(surprise)
10-NihX-Ray
-optimized CNN on FullDataset Nih-Xray
-MobileNet
-Transfer learning
-Capsule Network on FullDataset Nih-Xray
هزينه اين پكيج ٥٠٠هزار مي باشد و صرفا هزينه تهيه ديتاست هاست.
جهت خريد مي توانيد با ايدي بنده در ارتباط باشيد
@Raminmousa