Chapter

Dual Role Neural Graph Auto-encoder for CQA Recommendation

Authors:
To read the full-text of this research, you can request a copy directly from the authors.

Abstract

Matching between questions and suitable users is an appealing and challenging problem in the research area of community question answering (CQA). Usually, different from the traditional recommendation systems where a user has only a single role, each user in CQA can play two different roles (dual roles) simultaneously: as a requester and as an answerer. For different roles, users usually have varying interests and expertise in different topics and knowledge domains, which is rarely addressed in the previous methods. Besides, based on an explicit single link between two users, existing methods cannot capture implicit associations between their possibly similar roles. Therefore, in this paper, we propose the structure of a dual role graph and employ the link prediction approach to make CQA recommendation on the graph. Moreover, we develop a Dual Role Neural Graph auto-encoder (DRNGae) framework, which can: 1) encode the dual role graph structure to capture the implicit dual role correlation by propagating high-order information embeddings of graph neural network; 2) learn variable weights with the dual role feature preferences from dual role content information by self-attention mechanism; 3) reconstruct the graph structure to predict the possible interaction links. Experimental studies on real-world datasets verify our design and prove that our model achieves significantly better performance than baselines in link prediction (95.3% AUC, 96.2% AP on Citeseer dataset) and CQA recommendation (79.5% recall@25, 76.7% ndcg@25 on Yahoo! answer dataset).

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the authors.

ResearchGate has not been able to resolve any citations for this publication.
Conference Paper
Full-text available
Graph embedding is an effective method to represent graph data in a low dimensional space for graph analytics. Most existing embedding algorithms typically focus on preserving the topological structure or minimizing the reconstruction errors of graph data, but they have mostly ignored the data distribution of the latent codes from the graphs, which often results in inferior embedding in real-world graph data. In this paper, we propose a novel adversarial graph embedding framework for graph data. The framework encodes the topological structure and node content in a graph to a compact representation, on which a decoder is trained to reconstruct the graph structure. Furthermore, the latent representation is enforced to match a prior distribution via an adversarial training scheme. To learn a robust embedding, two variants of adversarial approaches, adversarially regularized graph autoencoder (ARGA) and adversarially regularized variational graph autoencoder (ARVGA), are developed. Experimental studies on real-world graphs validate our design and demonstrate that our algorithms outperform baselines by a wide margin in link prediction, graph clustering, and graph visualization tasks.
Conference Paper
Full-text available
This paper proposes AutoRec, a novel autoencoder framework for collaborative filtering (CF). Empirically, AutoRec's compact and efficiently trainable model outperforms state-of-the-art CF techniques (biased matrix factorization, RBM-CF and LLORMA) on the Movielens and Netflix datasets.
Conference Paper
Full-text available
Common approaches to problems involving multiple modalities (classification, retrieval, hyperlinking, etc.) are early fusion of the initial modalities and crossmodal translation from one modality to the other. Recently, deep neural networks, especially deep autoencoders, have proven promising both for crossmodal translation and for early fusion via multimodal embedding. In this work, we propose a flexible crossmodal deep neural network architecture for multimodal and crossmodal representation. By tying the weights of two deep neural networks, symmetry is enforced in central hidden layers thus yielding a multimodal representation space common to the two original representation spaces. The proposed architecture is evaluated in multimodal query expansion and multimodal retrieval tasks within the context of video hyperlinking. Our method demonstrates improved crossmodal translation capabilities and produces a multimodal embedding that significantly outperforms multimodal embeddings obtained by deep autoencoders, resulting in an absolute increase of 14.14 in precision at 10 on a video hyperlinking task.
Article
Full-text available
By making personalized suggestions, a recommender system is playing a crucial role in improving the engagement of users in modern web-services. However, most recommendation algorithms do not explicitly take into account the temporal behavior and the recurrent activities of users. Two central but less explored questions are how to recommend the most desirable item at the right moment,and how to predict the next returning time of a user to a service. To address these questions, we propose a novel framework which connects self-exciting point processes and low-rank models to capture the recurrent temporal patterns in a large collection of user-item consumption pairs. We show that the parameters of the model can be estimated via a convex optimization, and furthermore, we develop an efficient algorithm that maintains O(1/t) convergence rate, scales up to problems with millions of user-item pairs and thousands of millions of temporal events. Compared to other state-of-the-arts in both synthetic and real datasets, our model achieves superb predictive performance in the two time-sensitive recommendation questions. Finally, we point out that our formulation can incorporate other extra context information of users, such as profile, textual and spatial features.
Article
Full-text available
Question recommendation that automatically recommends a new question to suitable users to answer is an appealing and challenging problem in the research area of Community Question Answering (CQA). Unlike in general recommender systems where a user has only a single role, each user in CQA can play two different roles (dual roles) simultaneously: as an asker and as an answerer. To the best of our knowledge, this paper is the first to systematically investigate the distinctions between the two roles and their different influences on the performance of question recommendation in CQA. Moreover, we propose a Dual Role Model (DRM) to model the dual roles of users effectively. With different indepen-dence assumptions, two variants of DRM are achieved. Finally, we present the DRM based approach to question recommendation which provides a mechanism for naturally integrating the user relation between the answerer and the asker with the content re-levance between the answerer and the question into a uni-fied probabilistic framework. Experiments using a real-world data crawled from Yahoo! Answers show that: (1) there are evident distinctions between the two roles of users in CQA. Additionally, the answerer role is more effective than the asker role for modeling candidate users in question recommendation; (2) compared with baselines utilizing a single role or blended roles based methods, our DRM based approach consistently and significantly improves the performance of question recommendation, demonstrating that our approach can model the user in CQA more reasonably and precisely.
Conference Paper
Full-text available
Recommender systems can provide valuable services in a digital library environment, as demonstrated by its commercial success in book, movie, and music industries. One of the most commonly-used and successful recommendation algorithms is collaborative filtering, which explores the correlations within user-item interactions to infer user interests and preferences. However, the recommendation quality of collaborative filtering approaches is greatly limited by the data sparsity problem. To alleviate this problem we have previously proposed graph-based algorithms to explore transitive user-item associations. In this paper, we extend the idea of analyzing user-item interactions as graphs and employ link prediction approaches proposed in the recent network modeling literature for making collaborative filtering recommendations. We have adapted a wide range of linkage measures for making recommendations. Our preliminary experimental results based on a book recommendation dataset show that some of these measures achieved significantly better performance than standard collaborative filtering algorithms.
Article
Full-text available
Social media has reshaped the way in which people interact with each other. The rapid development of participatory web and social networking sites like YouTube, Twitter, and Facebook, also brings about many data mining opportunities and novel challenges. In particular, we focus on classification tasks with user interaction information in a social network. Networks in social media are heterogeneous, consisting of various relations. Since the relation-type information may not be available in social media, most existing approaches treat these inhomogeneous connections homogeneously, leading to an unsatisfactory classification performance. In order to handle the network heterogeneity, we propose the concept of social dimension to represent actors’ latent affiliations, and develop a classification framework based on that. The proposed framework, SocioDim, first extracts social dimensions based on the network structure to accurately capture prominent interaction patterns between actors, then learns a discriminative classifier to select relevant social dimensions. SocioDim, by differentiating different types of network connections, outperforms existing representative methods of classification in social media, and offers a simple yet effective approach to integrating two types of seemingly orthogonal information: the network of actors and their attributes.
Article
Full-text available
This paper presents a novel statistical method for factor analysis of binary and count data which is closely related to a technique known as Latent Semantic Analysis. In contrast to the latter method which stems from linear algebra and performs a Singular Value Decomposition of co-occurrence tables, the proposed technique uses a generative latent class model to perform a probabilistic mixture decomposition. This results in a more principled approach with a solid foundation in statistical inference. More precisely, we propose to make use of a temperature controlled version of the Expectation Maximization algorithm for model fitting, which has shown excellent performance in practice. Probabilistic Latent Semantic Analysis has many applications, most prominently in information retrieval, natural language processing, machine learning from text, and in related areas. The paper presents perplexity results for different types of text and linguistic data collections and discusses an application in automated document indexing. The experiments indicate substantial and consistent improvements of the probabilistic method over standard Latent Semantic Analysis.
Article
Most of the recent progresses on visual question answering are based on recurrent neural networks (RNNs) with attention. Despite the success, these models are often timeconsuming and having difficulties in modeling long range dependencies due to the sequential nature of RNNs. We propose a new architecture, Positional Self-Attention with Coattention (PSAC), which does not require RNNs for video question answering. Specifically, inspired by the success of self-attention in machine translation task, we propose a Positional Self-Attention to calculate the response at each position by attending to all positions within the same sequence, and then add representations of absolute positions. Therefore, PSAC can exploit the global dependencies of question and temporal information in the video, and make the process of question and video encoding executed in parallel. Furthermore, in addition to attending to the video features relevant to the given questions (i.e., video attention), we utilize the co-attention mechanism by simultaneously modeling “what words to listen to” (question attention). To the best of our knowledge, this is the first work of replacing RNNs with selfattention for the task of visual question answering. Experimental results of four tasks on the benchmark dataset show that our model significantly outperforms the state-of-the-art on three tasks and attains comparable result on the Count task. Our model requires less computation time and achieves better performance compared with the RNNs-based methods. Additional ablation study demonstrates the effect of each component of our proposed model.
Conference Paper
Recommender systems are vital ingredients for many e-commerce services. In the literature, two of the most popular approaches are based on factorization and graph-based models; the former approach captures user preferences by factorizing the observed direct interactions between users and items, and the latter extracts indirect preferences from the graphs constructed by user-item interactions. In this paper we present HOP-Rec, a unified and efficient method that incorporates the two approaches. The proposed method involves random surfing on a graph to harvest high-order information among neighborhood items for each user. Instead of factorizing a transition matrix, our method introduces a confidence weighting parameter to simulate all high-order information simultaneously, for which we maintain a sparse user-item interaction matrix and enrich the matrix for each user using random walks. Experimental results show that our approach significantly outperforms the state of the art on a range of large-scale real-world datasets.
Conference Paper
Item recommendation is a personalized ranking task. To this end, many recommender systems optimize models with pairwise ranking objectives, such as the Bayesian Personalized Ranking (BPR). Using matrix Factorization (MF) - the most widely used model in recommendation - as a demonstration, we show that optimizing it with BPR leads to a recommender model that is not robust. In particular, we find that the resultant model is highly vulnerable to adversarial perturbations on its model parameters, which implies the possibly large error in generalization. To enhance the robustness of a recommender model and thus improve its generalization performance, we propose a new optimization framework, namely Adversarial Personalized Ranking (APR). In short, our APR enhances the pairwise ranking method BPR by performing adversarial training. It can be interpreted as playing a minimax game, where the minimization of the BPR objective function meanwhile defends an adversary, which adds adversarial perturbations on model parameters to maximize the BPR objective function. To illustrate how it works, we implement APR on MF by adding adversarial perturbations on the embedding vectors of users and items. Extensive experiments on three public real-world datasets demonstrate the effectiveness of APR - by optimizing MF with APR, it outperforms BPR with a relative improvement of 11.2% on average and achieves state-of-the-art performance for item recommendation. Our implementation is available at: \urlhttps://github.com/hexiangnan/adversarial_personalized_ranking.
Article
The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. The best performing models also connect the encoder and decoder through an attention mechanism. We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely. Experiments on two machine translation tasks show these models to be superior in quality while being more parallelizable and requiring significantly less time to train. Our model achieves 28.4 BLEU on the WMT 2014 English-to-German translation task, improving over the existing best results, including ensembles by over 2 BLEU. On the WMT 2014 English-to-French translation task, our model establishes a new single-model state-of-the-art BLEU score of 41.0 after training for 3.5 days on eight GPUs, a small fraction of the training costs of the best models from the literature. We show that the Transformer generalizes well to other tasks by applying it successfully to English constituency parsing both with large and limited training data.
Article
We introduce the variational graph auto-encoder (VGAE), a framework for unsupervised learning on graph-structured data based on the variational auto-encoder (VAE). This model makes use of latent variables and is capable of learning interpretable latent representations for undirected graphs. We demonstrate this model using a graph convolutional network (GCN) encoder and a simple inner product decoder. Our model achieves competitive results on a link prediction task in citation networks. In contrast to most existing models for unsupervised learning on graph-structured data and link prediction, our model can naturally incorporate node features, which significantly improves predictive performance on a number of benchmark datasets.
Article
We present a scalable approach for semi-supervised learning on graph-structured data that is based on an efficient variant of convolutional neural networks which operate directly on graphs. We motivate the choice of our convolutional architecture via a localized first-order approximation of spectral graph convolutions. Our model scales linearly in the number of graph edges and learns hidden layer representations that encode both local graph structure and features of nodes. In a number of experiments on citation networks and on a knowledge graph dataset we demonstrate that our approach outperforms related methods by a significant margin.
Article
We present DeepWalk, a novel approach for learning latent representations of vertices in a network. These latent representations encode social relations in a continuous vector space, which is easily exploited by statistical models. DeepWalk generalizes recent advancements in language modeling and unsupervised feature learning (or deep learning) from sequences of words to graphs. DeepWalk uses local information obtained from truncated random walks to learn latent representations by treating walks as the equivalent of sentences. We demonstrate DeepWalk's latent representations on several multi-label network classification tasks for social networks such as BlogCatalog, Flickr, and YouTube. Our results show that DeepWalk outperforms challenging baselines which are allowed a global view of the network, especially in the presence of missing information. DeepWalk's representations can provide F1 scores up to 10% higher than competing methods when labeled data is sparse. In some experiments, DeepWalk's representations are able to outperform all baseline methods while using 60% less training data. DeepWalk is also scalable. It is an online learning algorithm which builds useful incremental results, and is trivially parallelizable. These qualities make it suitable for a broad class of real world applications such as network classification, and anomaly detection.
Conference Paper
Link prediction and recommendation is a fundamental problem in social network analysis. The key challenge of link prediction comes from the sparsity of networks due to the strong disproportion of links that they have potential to form to links that do form. Most previous work tries to solve the problem in single network, few research focus on capturing the general principles of link formation across heterogeneous networks. In this work, we give a formal definition of link recommendation across heterogeneous networks. Then we propose a ranking factor graph model (RFG) for predicting links in social networks, which effectively improves the predictive performance. Motivated by the intuition that people make friends in different networks with similar principles, we find several social patterns that are general across heterogeneous networks. With the general social patterns, we develop a transfer-based RFG model that combines them with network structure information. This model provides us insight into fundamental principles that drive the link formation and network evolution. Finally, we verify the predictive performance of the presented transfer model on 12 pairs of transfer cases. Our experimental results demonstrate that the transfer of general social patterns indeed help the prediction of links.
Conference Paper
Community Question Answering (CQA) service provides a platform for increasing number of users to ask and answer for their own needs but unanswered questions still exist within a fixed period. To address this, the paper aims to route questions to the right answerers who have a top rank in accordance of their previous answering performance. In order to rank the answerers, we propose a framework called Question Routing (QR) which consists of four phases: (1) performance profiling, (2) expertise estimation, (3) availability estimation, and (4) answerer ranking. Applying the framework, we conduct experiments with Yahoo! Answers dataset and the results demonstrate that on average each of 1,713 testing questions obtains at least one answer if it is routed to the top 20 ranked answerers.
Conference Paper
The rapidly increasing popularity of community-based Question Answering (cQA) services, e.g. Yahoo! Answers, Baidu Zhidao, etc. have attracted great attention from both academia and industry. Besides the basic problems, like question searching and answer finding, it should be noted that the low participation rate of users in cQA service is the crucial problem which limits its development potential. In this paper, we focus on addressing this problem by recommending answer providers, in which a question is given as a query and a ranked list of users is returned according to the likelihood of answering the question. Based on the intuitive idea for recommendation, we try to introduce topic-level model to improve heuristic term-level methods, which are treated as the baselines. The proposed approach consists of two steps: (1) discovering latent topics in the content of questions and answers as well as latent interests of users to build user profiles; (2) recommending question answerers for new arrival questions based on latent topics and term-level model. Specifically, we develop a general generative model for questions and answers in cQA, which is then altered to obtain a novel computationally tractable Bayesian network model. Experiments are carried out on a real-world data crawled from Yahoo! Answers during Jun 12 2007 to Aug 04 2007, which consists of 118510 questions, 772962 answers and 150324 users. The experimental results reveal significant improvements over the baseline methods and validate the positive influence of topic-level information.
Conference Paper
We propose to solve the link prediction problem in graphs using a supervised matrix factorization approach. The model learns latent features from the topological structure of a (possibly directed) graph, and is shown to make better predictions than popular unsupervised scores. We show how these latent features may be combined with optional explicit features for nodes or edges, which yields better performance than using either type of feature exclusively. Finally, we propose a novel approach to address the class imbalance problem which is common in link prediction by directly optimizing for a ranking loss. Our model is optimized with stochastic gradient descent and scales to large graphs. Results on several datasets show the efficacy of our approach.
Collective classification in network data
  • P Sen
  • G Namata
  • M Bilgic
  • L Getoor
  • B Galligher
  • T Eliassi-Rad