Fuli Feng

Computational Social Indicators: A Case Study of Chinese University Ranking

Many professional organizations produce regular reports of social indicators to monitor social progress. Despite their reasonable results and societal value, early efforts on social indicator computing suffer from three problems: 1) labor-intensive data gathering, 2) insufficient data, and 3) expert-relied data fusion. Towards this end, we present a novel graph-based multi-channel ranking scheme for social indicator computation by exploring the rich multi-channel Web data. For each channel, this scheme presents the semi-structured and unstructured data with simple graphs and hypergraphs, respectively. It then groups the channels into different clusters according to their correlations. After that, it uses a unified model to learn the cluster-wise common spaces, perform ranking separately upon each space, and fuse these rankings to produce the final one. We take Chinese university ranking as a case study and validate our scheme over a real-world dataset. It is worth emphasizing that our scheme is applicable to computation of other social indicators, such as Educational attainment.

NeuroStylist: Neural Compatibility Modeling for Clothing Matching

Nowadays, as a beauty-enhancing product, clothing plays an important role in humans social life. In fact, the key to a proper outfit usually lies in the harmonious clothing matching. Nevertheless, not everyone is good at clothing matching. Fortunately, with the proliferation of fashion-oriented online communities, fashion experts can publicly share their fashion tips by showcasing their outfit compositions, where each fashion item (e.g., a top or bottom) usually has an image and context metadata (e.g., title and category). Such rich fashion data offer us a new opportunity to investigate the code in clothing matching. However, challenges co-exist with opportunities. The first challenge lies in the complicated factors, such as color, material and shape, that affect the compatibility of fashion items. Second, as each fashion item involves multiple modalities (i.e., image and text), how to cope with the heterogeneous multi-modal data also poses a great challenge. Third, our pilot study shows that the composition relation between fashion items is rather sparse, which makes traditional matrix factorization methods not applicable. Towards this end, in this work, we propose a content-based neural scheme to model the compatibility between fashion items based on the Bayesian personalized ranking (BPR) framework. The scheme is able to jointly model the coherent relation between modalities of items and their implicit matching preference. Experiments verify the effectiveness of our scheme, and we deliver deep insights that can benefit future research.

Learning on Partial-Order Hypergraphs

Graph-based learning methods explicitly consider the relations between two entities (i.e., vertices) for learning the prediction function. They have been widely used in semi-supervised learning, manifold ranking, and clustering, among other tasks. Enhancing the expressiveness of simple graphs, hypergraphs formulate an edge as a link to multiple vertices, so as to model the higher-order relations among entities. For example, hyperedges in a hypergraph can be used to encode the similarity among vertices. To the best of our knowledge, all existing hypergraph structures represent the hyperedge as an unordered set of vertices, without considering the possible ordering relationship among vertices. In real-world data, ordering relations commonly exist, such as in graded categorical features (e.g., users» ratings on movies) and numerical features (e.g., monthly income of customers). When constructing a hypergraph, ignoring such ordering relations among entities will lead to severe information loss, resulting in suboptimal performance of the subsequent learning algorithms. In this work, we address the inherent limitation of existing hypergraphs by proposing a new data structure named Partial-Order Hypergraph, which specifically injects the partially ordering relations among vertices into a hyperedge. We develop regularization-based learning theories for partial-order hypergraphs, generalizing conventional hypergraph learning by incorporating logical rules that encode the partial-order relations. We apply our proposed method to two applications: university ranking from Web data and popularity prediction of online content. Extensive experiments demonstrate the superiority of our proposed partial-order hypergraphs, which consistently improve over conventional hypergraph methods.

TEM: Tree-enhanced Embedding Model for Explainable Recommendation

While collaborative filtering is the dominant technique in personalized recommendation, it models user-item interactions only and cannot provide concrete reasons for a recommendation. Meanwhile, the rich side information affiliated with user-item interactions (e.g., user demographics and item attributes), which provide valuable evidence that why a recommendation is suitable for a user, has not been fully explored in providing explanations. On the technical side, embedding-based methods, such as Wide&Deep and neural factorization machines, provide state-of-the-art recommendation performance. However, they work like a black-box, for which the reasons underlying a prediction cannot be explicitly presented. On the other hand, tree-based methods like decision trees predict by inferring decision rules from data. While being explainable, they cannot generalize to unseen feature interactions thus fail in collaborative filtering applications. In this work, we propose a novel solution named Tree-enhanced Embedding Method that combines the strengths of embedding-based and tree-based models. We first employ a tree-based model to learn explicit decision rules (aka. cross features) from the rich side information. We next design an embedding model that can incorporate explicit cross features and generalize to unseen cross features on user ID and item ID. At the core of our embedding method is an easy-to-interpret attention network, making the recommendation process fully transparent and explainable. We conduct experiments on two datasets of tourist attraction and restaurant recommendation, demonstrating the superior performance and explainability of our solution.

Depression Detection via Harvesting Social Media: A Multimodal Dictionary Learning Solution

Depression is a major contributor to the overall global burden of diseases. Traditionally, doctors diagnose depressed people face to face via referring to clinical depression criteria. However, more than 70% of the patients would not consult doctors at early stages of depression, which leads to further deterioration of their conditions. Meanwhile, people are increasingly relying on social media to disclose emotions and sharing their daily lives, thus social media have successfully been leveraged for helping detect physical and mental diseases. Inspired by these, our work aims to make timely depression detection via harvesting social media data. We construct well-labeled depression and non-depression dataset on Twitter, and extract six depression-related feature groups covering not only the clinical depression criteria, but also online behaviors on social media. With these feature groups, we propose a multimodal depressive dictionary learning model to detect the depressed users on Twitter. A series of experiments are conducted to validate this model, which outperforms (+3% to +10%) several baselines. Finally, we analyze a large-scale dataset on Twitter to reveal the underlying online behaviors between depressed and non-depressed users.

An Improved Sampler for Bayesian Personalized Ranking by Leveraging View Data

Bayesian Personalized Ranking (BPR) is a representative pairwise learning method for optimizing recommendation models. It is widely known that the performance of BPR depends largely on the quality of the negative sampler. In this short paper, we make two contributions with respect to BPR. First, we find that sampling negative items from the whole space is unnecessary and may even degrade the performance. Second, focusing on the purchase feedback of the E-commerce domain, we propose a simple yet effective sampler for BPR by leveraging the additional view data. Compared to the vanilla BPR that applies a uniform sampler on all candidates, our view-aware sampler enhances BPR with a relative improvement of 27.36% and 69.54% on two real-world datasets respectively.

Discrete Factorization Machines for Fast Feature-based Recommendation

User and item features of side information are crucial for accurate recommendation. However, the large number of feature dimensions, e.g., usually larger than 10^7, results in expensive storage and computational cost. This prohibits fast recommendation especially on mobile applications where the computational resource is very limited. In this paper, we develop a generic feature-based recommendation model, called Discrete Factorization Machine (DFM), for fast and accurate recommendation. DFM binarizes the real-valued model parameters (e.g., float32) of every feature embedding into binary codes (e.g., boolean), and thus supports efficient storage and fast user-item score computation. To avoid the severe quantization loss of the binarization, we propose a convergent updating rule that resolves the challenging discrete optimization of DFM. Through extensive experiments on two real-world datasets, we show that 1) DFM consistently outperforms state-of-the-art binarized recommendation models, and 2) DFM shows very competitive performance compared to its real-valued version (FM), demonstrating the minimized quantization loss. This work is accepted by IJCAI 2018.

Cross-Domain Depression Detection via Harvesting Social Media

Depression detection is a significant issue for human well-being. In previous studies, online detection has proven effective in Twitter, enabling proactive care for depressed users. Owing to cultural differences, replicating the method to other social media platforms, such as Chinese Weibo, however, might lead to poor performance because of insufficient available labeled (self-reported depression) data for model training. In this paper, we study an interesting but challenging problem of enhancing detection in a certain target domain (e.g. Weibo) with ample Twitter data as the source domain. We first systematically analyze the depression-related feature patterns across domains and summarize two major detection challenges, namely isomerism and divergency. We further propose a cross-domain Deep Neural Network model with Feature Adaptive Transformation & Combination strategy (DNN-FATC) that transfers the relevant information across heterogeneous domains. Experiments demonstrate improved performance compared to existing heterogeneous transfer methods or training directly in the target domain (over 3.4% improvement in F1), indicating the potential of our model to enable depression detection via social media for more countries with different cultural settings.

Quality Matters: Assessing cQA Pair Quality via Transductive Multi-View Learning

Community-based question answering (cQA) sites have become important knowledge sharing platforms, as massive cQA pairs are archived, but the uneven quality of cQA pairs leaves information seekers unsatisfied. Various efforts have been dedicated to predicting the quality of cQA contents. Most of them concatenate different features into single vectors and then feed them into regression models. In fact, the quality of cQA pairs is influenced by different views, and the agreement among them is essential for quality assessment. Besides, the lacking of labeled data significantly hinders the quality prediction performance. Toward this end, we present a transductive multi-view learning model. It is designed to find a latent common space by unifying and preserving information from various views, including question, answer, QA relevance, asker, and answerer. Additionally, rich information in the unlabeled test cQA pairs are utilized via transductive learning to enhance the representation ability of the common space. Extensive experiments on real-world datasets have wellvalidated the proposed model.

Neural Compatibility Modeling with Attentive Knowledge Distillation

Recently, the booming fashion sector and its huge potential benefits have attracted tremendous attention from many research communities. In particular, increasing research efforts have been dedicated to the complementary clothing matching as matching clothes to make a suitable outfit has become a daily headache for many people, especially those who do not have the sense of aesthetics. Thanks to the remarkable success of neural networks in various applications such as the image classification and speech recognition, the researchers are enabled to adopt the data-driven learning methods to analyze fashion items. Nevertheless, existing studies overlook the rich valuable knowledge (rules) accumulated in fashion domain, especially the rules regarding clothing matching. Towards this end, in this work, we shed light on the complementary clothing matching by integrating the advanced deep neural networks and the rich fashion domain knowledge. Considering that the rules can be fuzzy and different rules may have different confidence levels to different samples, we present a neural compatibility modeling scheme with attentive knowledge distillation based on the teacher-student network scheme. Extensive experiments on the real-world dataset show the superiority of our model over several state-of-the-art methods. Based upon the comparisons, we observe certain fashion insights that can add value to the fashion matching study. As a byproduct, we released the codes, and involved parameters to benefit other researchers.