Games have been a major focus of AI since the field formed seventy years ago. Recently, video games have replaced chess and go as the current "Mt. Everest Problem." This paper looks beyond the video games themselves to the application of AI techniques within the ecosystems that produce them. Electronic Arts (EA) must deal with AI at scale across many game studios as it develops many AAA games each year, and not a single, AI-based, flagship application. EA has adopted a horizontal scaling strategy in response to this challenge and built a platform for delivering AI artifacts anywhere within EA's software universe. By combining a data warehouse for player history, an Agent Store for capturing processes acquired through machine learning, and a recommendation engine as an action layer, EA has been delivering a wide range of AI solutions throughout the company during the last two years. These solutions, such as dynamic difficulty adjustment, in-game content and activity recommendations, matchmaking, and game balancing, have had major impact on engagement, revenue, and development resources within EA.

A user can be represented as what he/she does along the history. A common way to deal with the user modeling problem is to manually extract all kinds of aggregated features over the heterogeneous behaviors, which may fail to fully represent the data itself due to limited human instinct. Recent works usually use RNN-based methods to give an overall embedding of a behavior sequence, which then could be exploited by the downstream applications. However, this can only preserve very limited information, or aggregated memories of a person. When a downstream application requires to facilitate the modeled user features, it may lose the integrity of the specific highly correlated behavior of the user, and introduce noises derived from unrelated behaviors. This paper proposes an attention based user behavior modeling framework called ATRank, which we mainly use for recommendation tasks. Heterogeneous user behaviors are considered in our model that we project all types of behaviors into multiple latent semantic spaces, where influence can be made among the behaviors via self-attention. Downstream applications then can use the user behavior vectors via vanilla attention. Experiments show that ATRank can achieve better performance and faster training process. We further explore ATRank to use one unified model to predict different types of user behaviors at the same time, showing a comparable performance with the highly optimized individual models.

In this paper, we propose a unified framework and an algorithm for the problem of group recommendation where a fixed number of items or alternatives can be recommended to a group of users. The problem of group recommendation arises naturally in many real world contexts, and is closely related to the budgeted social choice problem studied in economics. We frame the group recommendation problem as choosing a subgraph with the largest group consensus score in a completely connected graph defined over the item affinity matrix. We propose a fast greedy algorithm with strong theoretical guarantees, and show that the proposed algorithm compares favorably to the state-of-the-art group recommendation algorithms according to commonly used relevance and coverage performance measures on benchmark dataset.

Privacy leakage is an important issue for social recommendation. Existing privacy preserving social recommendation approaches usually allow the recommender to fully control users' information. This may be problematic since the recommender itself may be untrusted, leading to serious privacy leakage. Besides, building social relationships requires sharing interests as well as other private information, which may lead to more privacy leakage. Although sometimes users are allowed to hide their sensitive private data using privacy settings, the data being shared can still be abused by the adversaries to infer sensitive private information. Supporting social recommendation with least privacy leakage to untrusted recommender and other users (i.e., friends) is an important yet challenging problem. In this paper, we aim to address the problem of achieving privacy-preserving social recommendation under personalized privacy settings. We propose PrivSR, a novel framework for privacy-preserving social recommendation, in which users can model ratings and social relationships privately. Meanwhile, by allocating different noise magnitudes to personalized sensitive and non-sensitive ratings, we can protect users' privacy against the untrusted recommender and friends. Theoretical analysis and experimental evaluation on real-world datasets demonstrate that our framework can protect users' privacy while being able to retain effectiveness of the underlying recommender system.

Review history is widely used by recommender systems to infer users' preferences and help find the potential interests from the huge volumes of data, whereas it also brings in great concerns on the sparsity and cold-start problems due to its inadequacy. Psychology and sociology research has shown that emotion information is a strong indicator for users' preferences. Meanwhile, with the fast development of online services, users are willing to express their emotion on others' reviews, which makes the emotion information pervasively available. Besides, recent research shows that the number of emotion on reviews is always much larger than the number of reviews. Therefore incorporating emotion on reviews may help to alleviate the data sparsity and cold-start problems for recommender systems. In this paper, we provide a principled and mathematical way to exploit both positive and negative emotion on reviews, and propose a novel framework MIRROR, exploiting eMotIon on Reviews for RecOmmendeR systems from both global and local perspectives. Empirical results on real-world datasets demonstrate the effectiveness of our proposed framework and further experiments are conducted to understand how emotion on reviews works for the proposed framework.

In designing personalized ranking algorithms, it is desirable to encourage a high precision at the top of the ranked list. Existing methods either seek a smooth convex surrogate for a non-smooth ranking metric or directly modify updating procedures to encourage top accuracy. In this work we point out that these methods do not scale well in a large-scale setting, and this is partly due to the inaccurate pointwise or pairwise rank estimation. We propose a new framework for personalized ranking. It uses batch-based rank estimators and smooth rank-sensitive loss functions. This new batch learning framework leads to more stable and accurate rank approximations compared to previous work. Moreover, it enables explicit use of parallel computation to speed up training. We conduct empirical evaluations on three item recommendation tasks, and our method shows a consistent accuracy improvement over current state-of-the-art methods. Additionally, we observe time efficiency advantages when data scale increases.

Traditional recommendation systems (RecSys) suffer from two problems: the exploitation-exploration dilemma and the cold-start problem. One solution to solving the exploitation-exploration dilemma is the contextual bandit policy, which adaptively exploits and explores user interests. As a result, the contextual bandit policy achieves increased rewards in the long run. The contextual bandit policy, however, may cause the system to explore more than needed in the cold-start situations, which can lead to worse short-term rewards. Cross-domain RecSys methods adopt transfer learning to leverage prior knowledge in a source RecSys domain to jump start the cold-start target RecSys. To solve the two problems together, in this paper, we propose the first applicable transferable contextual bandit (TCB) policy for the cross-domain recommendation. TCB not only benefits the exploitation but also accelerates the exploration in the target RecSys. TCB's exploration, in turn, helps to learn how to transfer between different domains. TCB is a general algorithm for both homogeneous and heterogeneous domains. We perform both theoretical regret analysis and empirical experiments. The empirical results show that TCB outperforms the state-of-the-art algorithms over time.

Peference elicitation is the task of suggesting a highly preferred configuration to a decision maker. The preferences are typically learned by querying the user for choice feedback over pairs or sets of objects. In its constructive variant, new objects are synthesized "from scratch" by maximizing an estimate of the user utility over a combinatorial (possibly infinite) space of candidates. In the constructive setting, most existing elicitation techniques fail because they rely on exhaustive enumeration of the candidates. A previous solution explicitly designed for constructive tasks comes with no formal performance guarantees, and can be very expensive in (or unapplicable to) problems with non-Boolean attributes. We propose the Choice Perceptron, a Perceptron-like algorithm for learning user preferences from set-wise choice feedback over constructive domains and hybrid Boolean-numeric feature spaces. We provide a theoretical analysis on the attained regret that holds for a large class of query selection strategies, and devise a heuristic strategy that aims at optimizing the regret in practice. Finally, we demonstrate its effectiveness by empirical evaluation against existing competitors on constructive scenarios of increasing complexity.

Modelling sparse and large data sets is highly in demand yet challenging in recommender systems. With the computation only on the non-zero ratings, Poisson Factorization (PF) enabled by variational inference has shown its high efficiency in scalable recommendation, e.g., modeling millions of ratings. However, as PF learns the ratings by individual users on items with the Gamma distribution, it cannot capture the coupling relations between users (items) and the rating popularity (i.e., favorable rating scores that are given to one item) and rating sparsity (i.e., those users (items) with many zero ratings) for one item (user). This work proposes Coupled Poisson Factorization (CPF) to learn the couplings between users (items), and the user/item attributes (i.e., metadata) are integrated into CPF to form the Metadata-integrated CPF (mCPF) to not only handle sparse but also popular ratings in very large-scale data. Our empirical results show that the proposed models significantly outperform PF and address the key limitations in PF for scalable recommendation.

Multi-task learning (MTL) is a machine learning paradigm that improves the performance of each task by exploiting useful information contained in multiple related tasks. However, the relatedness of tasks can be exploited by attackers to launch data poisoning attacks, which has been demonstrated a big threat to single-task learning. In this paper, we provide the first study on the vulnerability of MTL. Specifically, we focus on multi-task relationship learning (MTRL) models, a popular subclass of MTL models where task relationships are quantized and are learned directly from training data. We formulate the problem of computing optimal poisoning attacks on MTRL as a bilevel program that is adaptive to arbitrary choice of target tasks and attacking tasks. We propose an efficient algorithm called PATOM for computing optimal attack strategies. PATOM leverages the optimality conditions of the subproblem of MTRL to compute the implicit gradients of the upper level objective function. Experimental results on real-world datasets show that MTRL models are very sensitive to poisoning attacks and the attacker can significantly degrade the performance of target tasks, by either directly poisoning the target tasks or indirectly poisoning the related tasks exploiting the task relatedness. We also found that the tasks being attacked are always strongly correlated, which provides a clue for defending against such attacks.