Overcome underfitting on train data using CNN architecture

Question

I use 2 layer CNN network for NLP task with triplet loss with margin 0.2. The task is to learn document embeddings to find similar docs. My architecture is similar to this https://arxiv.org/abs/1406.3830

I use truncated_normal init function from TensorFlow to initialize conv weights. I also use AdamOptimizer with default params. Then I subsample small (or big) dataset and use 5-10 epochs to train on it. But the loss stays close to 0.2 all the time. I am defiantly underfitting. But the underfitting is not related to insufficient number of layers because same architecture works fine in literature. The problem I guess is the initialization function of convolution layers weights - it is just stuck in some local minimum. But I don't know for sure.

Where is my mistake? What is a good way to init my conv layers?

Answer 1

The problem was my mistake. I did not compose triples properly, there was no anchor, positive and negative examples, they were all anchors or positives or negatives. My mistake. That is why neural net could not find no way to optimize. After I fixed this mistake the loss went down as expected and it started to overfit, luckily.