# DeepCas

**Repository Path**: wu58814/DeepCas

## Basic Information

- **Project Name**: DeepCas
- **Description**: No description available
- **Primary Language**: Python
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 1
- **Forks**: 0
- **Created**: 2020-10-29
- **Last Updated**: 2022-06-10

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# DeepCas

Adopted to `Python3 `and `tensorflow1`, removed the `lua` files.

This repository provides a reference implementation of [*DeepCas* as described in the paper](https://arxiv.org/abs/1611.05373):
	
	DeepCas: an End-to-end Predictor of Information Cascades
	Cheng Li, Jiaqi Ma, Xiaoxiao Guo and Qiaozhu Mei
	World wide web (WWW), 2017

The *DeepCas* algorithm learns the representation of cascade graphs in an end-to-end manner for cascade prediction.

## Structure of Data

Each dataset in a directory of `data`.

Files in data:

- cascasdes used in train, validation and test:

  - `cascade_test.txt`
  - `cascade_train.txt`
  - `cascade_val.txt`

  Format:
  > graph_id \t [author_id ] \t org_date \t num_nodes \t [source:target:weight ] \t [label ]
  
  The `weight` set to 1, `author_id` and `org_date` are not used in algorithm, keep it blank is ok.

- all edges in global graph(all cascades in one graph):
  - `global_graph.txt`

  Format:
  > node_id \t\t null|[target_id:freq \t ]

  The `freq` means the number of times an edge appears in a graph with multiple edges.  In `test-net`, many edges are not reflected in the cascade.

## Tensorflow Implementation

### Prerequisites

- Tensorflow ~~0.12.1~~ **1.15**
- python 3.6.2
- gensim 2.3.0
- netwotrkx 1.11

See `requirements.txt` for more details.

Also, vitual environments in `Anaconda` is recommend, see `environment.yml` for more detail.

### Basic Usage

To run *DeepCas* tensorflow version on a test data set, execute the following command:

```{r, engine='bash', count_lines}
cd DeepCas
python gen_walks/gen_walks.py --dataset test-net
cd tensorflow
python preprocess.py
python run.py
```

You can use `python run.py | tee output.txt` for saving the output to file `output.txt` while keeping print to screen(for powershell).

## Citing

If you find *DeepCas* useful for your research, please consider citing the following paper:

	@inproceedings{DeepCas-www2017,
	author = {Li, Cheng and Ma, Jiaqi and Guo, Xiaoxiao and Mei, Qiaozhu},
	 title = {DeepCas: an End-to-end Predictor of Information Cascades},
	 booktitle = {Proceedings of the 26th international conference on World wide web},
	 year = {2017}
	}

## Miscellaneous

Please send any questions you might have about the code and/or the algorithm to <lichengz@umich.edu>.