To maximize cumulative user engagement (e.g. cumulative clicks) in sequential recommendation, it is often needed to tradeoff two potentially conflicting objectives, that is, pursuing higher immediate user engagement (e.g., click-through rate) and encouraging user browsing (i.e., more items exposured). Existing works often study these two tasks separately, thus tend to result in sub-optimal results. In this paper, we study this problem from an online optimization perspective, and propose a flexible and practical framework to explicitly tradeoff longer user browsing length and high immediate user engagement. Specifically, by considering items as actions, user's requests as states and user leaving as an absorbing state, we formulate each user's behavior as a personalized Markov decision process (MDP), and the problem of maximizing cumulative user engagement is reduced to a stochastic shortest path (SSP) problem. Meanwhile, with immediate user engagement and quit probability estimation, it is shown that the SSP problem can be efficiently solved via dynamic programming. Experiments on real-world datasets demonstrate the effectiveness of the proposed approach. Moreover, this approach is deployed at a large E-commerce platform, achieved over 7% improvement of cumulative clicks.

Multinomial logit bandit is a sequential subset selection problem which arises in many applications. In each round, the player selects a K-cardinality subset from N candidate items, and receives a reward which is governed by a multinomial logit (MNL) choice model considering both item utility and substitution property among items. The player's objective is to dynamically learn the parameters of MNL model and maximize cumulative reward over a finite horizon T. This problem faces the exploration-exploitation dilemma, and the involved combinatorial nature makes it non-trivial. In recent years, there have developed some algorithms by exploiting specific characteristics of the MNL model, but all of them estimate the parameters of MNL model separately and incur a regret bound which is not preferred for large candidate set size N. In this paper, we consider the linear utility MNL choice model whose item utilities are represented as linear functions of d-dimension item features, and propose an algorithm, titled LUMB, to exploit the underlying structure. It is proven that the proposed algorithm achieves regret which is free of candidate set size. Experiments show the superiority of the proposed algorithm.

Graph embedding algorithms embed a graph into a vector space where the structure and the inherent properties of the graph are preserved. The existing graph embedding methods cannot preserve the asymmetric transitivity well, which is a critical property of directed graphs. Asymmetric transitivity depicts the correlation among directed edges, that is, if there is a directed path from u to v, then there is likely a directed edge from u to v. Asymmetric transitivity can help in capturing structures of graphs and recovering from partially observed graphs. To tackle this challenge, we propose the idea of preserving asymmetric transitivity by approximating high-order proximity which are based on asymmetric transitivity. In particular, we develop a novel graph embedding algorithm, High-Order Proximity preserved Embedding (HOPE for short), which is scalable to preserve high-order proximities of large scale graphs and capable of capturing the asymmetric transitivity. More specifically, we first derive a general formulation that cover multiple popular high-order proximity measurements, then propose a scalable embedding algorithm to approximate the high-order proximity measurements based on their general formulation. Moreover, we provide a theoretical upper bound on the RMSE (Root Mean Squared Error) of the approximation. Our empirical experiments on a synthetic dataset and three real-world datasets demonstrate that HOPE can approximate the high-order proximities significantly better than the state-of-art algorithms and outperform the state-of-art algorithms in tasks of reconstruction, link prediction and vertex recommendation.

Due to the simplicity and efficiency, many hashing methods have recently been developed for large-scale similarity search. Most of the existing hashing methods focus on mapping low-level features to binary codes, but neglect attributes that are commonly associated with data samples. Attribute data, such as image tag, product brand, and user profile, can represent human recognition better than low-level features. However, attributes have specific characteristics, including high-dimensional, sparse and categorical properties, which is hardly leveraged into the existing hashing learning frameworks. In this paper, we propose a hashing learning framework, Probabilistic Attributed Hashing (PAH), to integrate attributes with low-level features. The connections between attributes and low-level features are built through sharing a common set of latent binary variables, i.e. hash codes, through which attributes and features can complement each other. Finally, we develop an efficient iterative learning algorithm, which is generally feasible for large-scale applications. Extensive experiments and comparison study are conducted on two public datasets, i.e., DBLP and NUS-WIDE. The results clearly demonstrate that the proposed PAH method substantially outperforms the peer methods.

Approximating the semantic similarity between entities in the learned Hamming space is the key for supervised hashing techniques. The semantic similarities between entities are often non-transitive since they could share different latent similarity components. For example, in social networks, we connect with people for various reasons, such as sharing common interests, working in the same company, being alumni and so on. Obviously, these social connections are non-transitive if people are connected due to different reasons. However, existing supervised hashing methods treat the pairwise similarity relationships in a simple and unified way and project data into a single Hamming space, while neglecting that the non-transitive property cannot be ade- quately captured by a single Hamming space. In this paper, we propose a non-transitive hashing method, namely Multi-Component Hashing (MuCH), to identify the latent similarity components to cope with the non-transitive similarity relationships. MuCH generates multiple hash tables with each hash table corresponding to a similarity component, and preserves the non-transitive similarities in different hash table respectively. Moreover, we propose a similarity measure, called Multi-Component Similarity, aggregating Hamming similarities in multiple hash tables to capture the non-transitive property of semantic similarity. We conduct extensive experiments on one synthetic dataset and two public real-world datasets (i.e. DBLP and NUS-WIDE). The results clearly demonstrate that the proposed MuCH method significantly outperforms the state-of-art hashing methods especially on search efficiency.

As large-scale multimodal data are ubiquitous in many real-world applications, learning multimodal representations for efficient retrieval is a fundamental problem. Most existing methods adopt shallow structures to perform multimodal representation learning. Due to a limitation of learning ability of shallow structures, they fail to capture the correlation of multiple modalities. Recently, multimodal deep learning was proposed and had proven its superiority in representing multimodal data due to its high nonlinearity. However, in order to learn compact and accurate representations, how to reduce the redundant information lying in the multimodal representations and incorporate different complexities of different modalities in the deep models is still an open problem. In order to address the aforementioned problem, in this paper we propose a hashing-based orthogonal deep model to learn accurate and compact multimodal representations. The method can better capture the intra-modality and inter-modality correlations to learn accurate representations. Meanwhile, in order to make the representations compact, the hashing-based model can generate compact hash codes and the proposed orthogonal structure can reduce the redundant information lying in the codes by imposing orthogonal regularizer on the weighting matrices. We also theoretically prove that, in this case, the learned codes are guaranteed to be approximately orthogonal. Moreover, considering the different characteristics of different modalities, effective representations can be attained with different number of layers for different modalities. Comprehensive experiments on three real-world datasets demonstrate a substantial gain of our method on retrieval tasks compared with existing algorithms.

Although hashing techniques have been popular for the large scale similarity search problem, most of the existing methods for designing optimal hash functions focus on homogeneous similarity assessment, i.e., the data entities to be indexed are of the same type. Realizing that heterogeneous entities and relationships are also ubiquitous in the real world applications, there is an emerging need to retrieve and search similar or relevant data entities from multiple heterogeneous domains, e.g., recommending relevant posts and images to a certain Facebook user. In this paper, we address the problem of ``comparing apples to oranges'' under the large scale setting. Specifically, we propose a novel Relation-aware Heterogeneous Hashing (RaHH), which provides a general framework for generating hash codes of data entities sitting in multiple heterogeneous domains. Unlike some existing hashing methods that map heterogeneous data in a common Hamming space, the RaHH approach constructs a Hamming space for each type of data entities, and learns optimal mappings between them simultaneously. This makes the learned hash codes flexibly cope with the characteristics of different data domains. Moreover, the RaHH framework encodes both homogeneous and heterogeneous relationships between the data entities to design hash functions with improved accuracy. To validate the proposed RaHH method, we conduct extensive evaluations on two large datasets; one is crawled from a popular social media sites, Tencent Weibo, and the other is an open dataset of Flickr(NUS-WIDE). The experimental results clearly demonstrate that the RaHH outperforms several state-of-the-art hashing methods with significant performance gains.

People and information are two core dimensions in a social network. People sharing information (such as blogs, news, albums, etc.) is the basic behavior. In this paper, we focus on predicting item-level social influence to answer the question Who should share What, which can be extended into two information retrieval scenarios: (1) Users ranking: given an item, who should share it so that its diffusion range can be maximized in a social network; (2) Web posts ranking: given a user, what should she share to maximize her influence among her friends. We formulate the social influence prediction problem as the estimation of a user-post matrix, in which each entry represents the strength of influence of a user given a web post. We propose a Hybrid Factor Non-Negative Matrix Factorization (HF-NMF) approach for item-level social influence modeling, and devise an efficient projected gradient method to solve the HF-NMF problem. Intensive experiments are conducted and demonstrate the advantages and characteristics of the proposed method.