Task-Guided and Path-Augmented Heterogeneous Network Embedding for Author Identification
By Ting-Li Chen, Yizhou Sun. 2016
229 citations recorded by the source corpus.
In this paper, we study the problem of author identification under double-blind review setting, which is to identify potential authors given information of an anonymized paper. Different from existing approaches that rely heavily on feature engineering, we propose to use network embedding approach to address the problem, which can automatically represent nodes into lower dimensional feature vectors. However, there are two major limitations in recent studies on network embedding: (1) they are usually general-purpose embedding methods, which are independent of the specific tasks; and (2) most of these approaches can only deal with homogeneous networks, where the heterogeneity of the network is ignored. Hence, challenges faced here are two folds: (1) how to embed the network under the guidance of the author identification task, and (2) how to select the best type of information due to the heterogeneity of the network. To address the challenges, we propose a task-guided and path-augmented heterogeneous network embedding model. In our model, nodes are first embedded as vectors in latent feature space. Embeddings are then shared and jointly trained according to task-specific and network-general objectives. We extend the existing unsupervised network embedding to incorporate meta paths in heterogeneous networks, and select paths according to the specific task. The guidance from author identification task for network embedding is provided both explicitly in joint training and implicitly during meta path selection. Our experiments demonstrate that by using path-augmented network embedding with task guidance, our model can obtain significantly better accuracy at identifying the true authors comparing to existing methods.
Subfields: Artificial Intelligence, Graph Learning
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
In Graph Learning
Citations in the corpus
- On Sampling Strategies for Neural Network-based Collaborative Filtering (2017, methodology): “Compared to traditional feature detectors, such as SIFT and n-grams, DNNs and other embedding methods [5, 6, 29] can automatically extract better features that produce higher performance in various tasks.”
- Joint Text Embedding for Personalized Content-based Recommendation (2017, background): “Recent advances in deep learning have demonstrated the importance of learning good representations for text and other types of data [2, 4, 12, 16, 18, 19].”
- Bridging Collaborative Filtering and Semi-Supervised Learning: A Neural Approach for POI Recommendation (2017, background): “e recent work [5] also shows promising results by leveraging unlabeled data from heterogeneous graphs.”
- metapath2vec: Scalable Representation Learning for Heterogeneous Networks (2017, methodology): “In addition, several other methods have been proposed for learning representations in networks [4, 5, 11, 20, 23].”
- Heterogeneous Graph Neural Network (2019, background): “[2] designed a HetG based ranking model to identify authors of anonymous papers.”
- Heterogeneous Information Network Embedding for Recommendation (2017, background): “Recently, several works [54], [55], [56], [57], [58] attempt to analyze heterogeneous networks via embedding methods.”
- A Survey on Network Embedding (2017, background): “Some recent works demonstrate the feasibility in applications such as cascading prediction (Li et al. 2017), anomaly detection (Hu et al. 2016), network alignment (Man et al. 2016) and collaboration prediction (Chen and Sun 2017).”
- Representation Learning for Dynamic Graphs: A Survey (2019, methodology): “Instead of hand-crafting meta-paths, Chen and Sun (2017) propose a greedy approach to select the meta-paths based on performance on a validation set.”