DSSM

Introduction

[paper]

Title: Learning deep structured semantic models for web search using clickthrough data

Authors: Po-Sen Huang, Xiaodong He, Jianfeng Gao, Li Deng, Alex Acero, Larry Heck

Abstract: Latent semantic models, such as LSA, intend to map a query to its relevant documents at the semantic level where keyword-based matching often fails. In this study we strive to develop a series of new latent semantic models with a deep structure that project queries and documents into a common low-dimensional space where the relevance of a document given a query is readily computed as the distance between them. The proposed deep structured semantic models are discriminatively trained by maximizing the conditional likelihood of the clicked documents given a query using the clickthrough data.

To make our models applicable to large-scale Web search applications, we also use a technique called word hashing, which is shown to effectively scale up our semantic models to handle large vocabularies which are common in such tasks. The new models are evaluated on a Web document ranking task using a real-world data set. Results show that our best model significantly outperforms other latent semantic models, which were considered state-of-the-art in the performance prior to the work presented in this paper.

../../../_images/dssm.png

Running with RecBole

Model Hyper-Parameters:

  • embedding_size (int) : The embedding size of features. Defaults to 10.

  • mlp_hidden_size (list of int) : The hidden size of MLP layers. Defaults to [256, 256, 256].

  • dropout_prob (float) : The dropout rate of edge in the linear predict layer. Defaults to 0.3.

  • double_tower (bool) : Whether or not to use the double-tower mode. Defaults to True.

A Running Example:

Write the following code to a python file, such as run.py

from recbole.quick_start import run_recbole

run_recbole(model='DSSM', dataset='ml-100k')

And then:

python run.py

Notes:

  • DSSM requires user-side and item-side features.

Tuning Hyper Parameters

If you want to use HyperTuning to tune hyper parameters of this model, you can copy the following settings and name it as hyper.test.

learning_rate choice [0.01,0.005,0.001,0.0005,0.0001]
dropout_prob choice [0.0,0.1,0.2,0.3,0.4,0.5]
mlp_hidden_size choice ['[64,64,64]','[128,128,128]','[256,256,256]','[512,512,512]']

Note that we just provide these hyper parameter ranges for reference only, and we can not guarantee that they are the optimal range of this model.

Then, with the source code of RecBole (you can download it from GitHub), you can run the run_hyper.py to tuning:

python run_hyper.py --model=[model_name] --dataset=[dataset_name] --config_files=[config_files_path] --params_file=hyper.test

For more details about Parameter Tuning, refer to Parameter Tuning.

If you want to change parameters, dataset or evaluation settings, take a look at