DeepCity: A Feature Learning Framework for Mining Location Check-Ins

By Jun Pang, Yang Zhang. 2016

31 citations recorded by the source corpus.

Online social networks being extended to geographical space has resulted in large amount of user check-in data. Understanding check-ins can help to build appealing applications, such as location recommendation. In this paper, we propose DeepCity, a feature learning framework based on deep learning, to profile users and locations, with respect to user demographics and location category prediction. Both of the predictions are essential for social network companies to increase user engagement. The key contribution of DeepCity is the proposal of task-specific random walk which uses the location and user properties to guide the feature learning to be specific to each prediction task. Experiments conducted on 42M check-ins in three cities collected from Instagram have shown that DeepCity achieves a superior performance and outperforms state-of-the-art models significantly.

Subfields: Information Systems, Statistical and Nonlinear Physics, Transportation

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Information Systems

1. Congzheng Song
2. Vitaly Shmatikov
3. Michael Backes
4. Mathias Humbert
5. Luca Melis
6. Emiliano De Cristofaro
7. Mario Fritz
8. Yang Zhang

In Statistical and Nonlinear Physics

1. Michael Backes
2. Mathias Humbert
3. Vitaly Shmatikov
4. Emiliano De Cristofaro
5. Mario Fritz
6. Yang Zhang
7. Congzheng Song
8. Tianhao Wang

In Transportation

1. Michael Backes
2. Mathias Humbert
3. Vitaly Shmatikov
4. Emiliano De Cristofaro
5. Yang Zhang
6. Congzheng Song

Citations in the corpus

• Exploiting Unintended Feature Leakage in Collaborative Learning (2018, neutral): “The model is a gender classifier, a task previously studied by Pang et al. [44] on similar datasets.”
• ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models (2018, methodology): “d, we adopt the AUC (area under the ROC curve) value, which reports the relation between true positive rate and false negative rate over multiple thresholds, as the evaluation metric [13], [3], [35], [32], [49]. Besides maximal posterior probability, we further test the effect of using other statist”
• Inference Attacks Against Collaborative Learning (2018, background): “ed in at least 10 different locations in New York City and for whom we know their gender [65]. This yields 528,878 check-ins. The model is a gender classifier, a task previously studied by Pang et al. [44] on similar datasets. CLiPS Stylometry Investigation (CSI) Corpus. This annually expanded datase”
• When Machine Unlearning Jeopardizes Privacy (2020, methodology): “ack and classical membership inference. To summarize, we have the following three metrics: AUC. It is a widely used metric to measure the performance of binary classification in a range of thresholds [6,15,22,30,41,42,46,49,64,66]. It tells how much the attack model is capable of distinguishing betwe”