Understanding Variational Graph Auto-Encoders

January 17, 2019January 17, 2019 ~ Irene ~ 2 Comments

Variational Auto-Encoders

My post about Auto-encoder.
For Variational Auto-Encoders (VAE) (from paper Auto-Encoding Variational Bayes), we actually add latent variables to the existing Autoencoders. The main idea is, we want to restrict the parameters from a known distribution. Why we want this? We wish the generative model to provide more “creative” things. If the model only sees the trained samples, it will eventually lose the ability to “create” more! So we add some “noises” to the parameters by forcing the parameters to adapt to a known distribution.

Continue reading “Understanding Variational Graph Auto-Encoders” →

Understanding Graph Convolutional Networks

January 8, 2019January 9, 2019 ~ Irene ~ 1 Comment

Why Graphs?

Graph Convolution Networks (GCNs) [0] deal with graphs where the data form with a graph structure. A typical graph is represented as G(V, E), where V is the collection of all the nodes and Eis the collection of all the edges.

Continue reading “Understanding Graph Convolutional Networks” →

Slideshare (4): A brief Introduction on Transfer Learning

September 13, 2018 ~ Irene ~ Leave a comment

Please check my notes for Transfer Learning introduction!

Transfer Learning

Transfer Learning Materials

August 9, 2018March 19, 2019 ~ Irene ~ Leave a comment

Keep Updating

Continue reading “Transfer Learning Materials” →

Slideshare (3): Unsupervised Transfer Learning Methods

July 19, 2018July 19, 2018 ~ Irene ~ Leave a comment

A brief introduction on unsupervised transfer learning methods.

The presentation focused on unsupervised transfer learning methods, introducing feature-based and model-based strategies and few recent papers from ICML, ACL.

Unsupervised Transfer Learning

Comments are welcomed!

TensorFlow 08: save and restore a subset of variables

July 13, 2018January 11, 2019 ~ Irene ~ Leave a comment

TensorFlow provides save and restore functions for us to save and re-use the model parameters. If you have a trained VGG model, for example, it will be helpful for you to restore the first few layers then apply them in your own networks. This may raise a problem, how do we restore a subset of the parameters? You can always check the TF official document here. In this post, I will take some code from the document and add some practical points.

Continue reading “TensorFlow 08: save and restore a subset of variables” →

To copy or not, that is the question: copying mechanism

June 25, 2018 ~ Irene ~ 3 Comments

In our daily life, we always repeating something mentioned before in our dialogue, like the name of people or organizations. “Hi, my name is Pikachu”, “Hi, Pikachu,…” There is a high probability that the word “Pikachu” will not be in the vocabulary extracted from the training data. So in the paper (Incorporating Copying Mechanism in Sequence-to-Sequence Learning), the authors proposed CopyNet which brings copying mechanism to seq2seq models with encoder and decoder structure. Read from my old post to learn the prerequisite knowledge.

Continue reading “To copy or not, that is the question: copying mechanism” →