User embeddings (vectorized representations of a user) are essential in recommendation systems. Numerous approaches have been proposed to construct a representation for the user in order to find similar items for retrieval tasks, and they have been proven effective in industrial recommendation systems. Recently people have discovered the power of using multiple embeddings to represent a user, with the hope that each embedding represents the user's interest in a certain topic. With multi-interest representation, it's important to model the user's preference over the different topics and how the preference changes with time. However, existing approaches either fail to estimate the user's affinity to each interest or unreasonably assume every interest of every user fades at an equal rate with time, thus hurting the performance of candidate retrieval. In this paper, we propose the Multi-Interest Preference (MIP) model, an approach that not only produces multi-interest for users by using the user's sequential engagement more effectively but also automatically learns a set of weights to represent the preference over each embedding so that the candidates can be retrieved from each interest proportionally. Extensive experiments have been done on various industrial-scale datasets to demonstrate the effectiveness of our approach.

Modern recommender systems usually include separate recommendation carousels such as ‘trending now’ to list trending items and further boost their popularity, thereby attracting active users. Though widely useful, such ‘trending now’ carousels typically generate item lists based on simple heuristics, e.g., the number of interactions within a time interval, and therefore still leave much room for improvement. This paper aims to systematically study this under-explored but important problem from the new perspective of time series forecasting. We first provide a set of rigorous definitions related to item trendiness and formulate the trend recommendation task as a one-step time series forecasting problem. We then propose a deep latent variable model, dubbed Trend Recommender (TrendRec), to forecast items’ future trends and generate trending item lists. Furthermore, we design associated evaluation protocols for trend recommendation. Experiments on real-world datasets from various domains show that our TrendRec significantly outperforms the baselines, verifying our model’s effectiveness.

We present a first step towards developing an interactive piano tutoring system that can observe a student playing the piano and give feedback about hand movements and musical accuracy. In particular, we have two primary aims: 1) to determine which notes on a piano are being played at any moment in time, 2) to identify which finger is pressing each note. We introduce a novel two-stream convolutional neural network that takes video and audio inputs together for detecting pressed notes and finger presses. We formulate our two problems in terms of multi-task learning and extend a state-of-the-art object detection model to incorporate both audio and visual features. In addition, we introduce a novel finger identification solution based on pressed piano note information. We experimentally confirm that our approach is able to detect pressed piano keys and the piano player's fingers with a high accuracy.

Network embedding algorithms that map nodes in a network into a low-dimensional vector space are prevalent in recent years, due to their superior performance in many network-based tasks, such as clustering, classification, and link prediction. The main assumption of existing algorithms is that the learned latent representation for nodes should preserve the structure of the network, in terms of first-order or higher-order connectivity. In other words, nodes that are more similar will have higher probability to connect to each other. This phenomena is typically explained as homophily in network science. However, there is another factor usually neglected by the existing embedding algorithms, which is the popularity of a node. For example, celebrities in a social network usually receive numerous followers, which cannot be fully explained by the similarity of the two users. We denote this factor with the terminology "social rank»». We then propose a network embedding model that considers both of the two factors in link generation, and learn proximity-based embedding and social rank-based embedding separately. Rather than simply treating these two factors independent with each other, a carefully designed link generation model is proposed, which explicitly models the interdependency between these two types of embeddings. Experiments on several real-world datasets across different domains demonstrate the superiority of our novel network embedding model over the state-of-the-art methods.

Social media websites have become a popular outlet for online users to express their opinions on controversial issues, such as gun control and abortion. Understanding users' stances and their arguments is a critical task for policy-making process and public deliberation. Existing methods rely on large amounts of human annotation for predicting stance on issues of interest, which is expensive and hard to scale to new problems. In this work, we present a weakly-guided user stance modeling framework which simultaneously considers two types of information: what do you say (via stance-based content generative model) and how do you behave (via social interaction-based graph regularization). We experiment with two types of social media data: news comments and discussion forum posts. Our model uniformly outperforms a logistic regression-based supervised method on stance-based link prediction for unseen users on news comments. Our method also achieves better or comparable stance prediction performance for discussion forum users, when compared with state-of-the-art supervised systems. Meanwhile, separate word distributions are learned for users of opposite stances. This potentially helps with better understanding and interpretation of conflicting arguments for controversial issues.

Almost all real-world social networks are dynamic and evolving with time, where new links may form and old links may drop, largely determined by the homophily of social actors (i.e., nodes in the network). Meanwhile, (latent) properties of social actors, such as their opinions, are changing along the time, partially due to social influence received from the network, which will in turn affect the network structure. Social network evolution and node property migration are usually treated as two orthogonal problems, and have been studied separately. In this paper, we propose a co-evolution model that closes the loop by modeling the two phenomena together, which contains two major components: (1) a network generative model when the node property is known; and (2) a property migration model when the social network structure is known. Simulation shows that our model has several nice properties: (1) it can model a broad range of phenomena such as opinion convergence (i.e., herding) and community-based opinion divergence; and (2) it allows to control the evolution via a set of factors such as social influence scope, opinion leader, and noise level. Finally, the usefulness of our model is demonstrated by an application of co-sponsorship prediction for legislative bills in Congress, which outperforms several state-of-the-art baselines.

Recommender systems typically leverage two types of signals to effectively recommend items to users: user activities and content matching between user and item profiles, and recommendation models in literature are usually categorized into collaborative filtering models, content-based models and hybrid models. In practice, when rich profiles about users and items are available, and user activities are sparse (cold-start), effective content matching signals become much more important in the relevance of the recommendation. The de-facto method to measure similarity between two pieces of text is computing the cosine similarity of the two bags of words, and each word is weighted by TF (term frequency within the document) x IDF (inverted document frequency of the word within the corpus). In general sense, TF can represent any local weighting scheme of the word within each document, and IDF can represent any global weighting scheme of the word across the corpus. In this paper, we focus on the latter, i.e., optimizing the global term weights, for a particular recommendation domain by leveraging supervised approaches. The intuition is that some frequent words (lower IDF, e.g. ``database'') can be essential and predictive for relevant recommendation, while some rare words (higher IDF, e.g. the name of a small company) could have less predictive power. Given plenty of observed activities between users and items as training data, we should be able to learn better domain-specific global term weights, which can further improve the relevance of recommendation.

Ideal point estimation that estimates legislators' ideological positions and understands their voting behavior has attracted studies from political science and computer science. Typically, a legislator is assigned a global ideal point based on her voting or other social behavior. However, it is quite normal that people may have different positions on different policy dimensions. For example, some people may be more liberal on economic issues while more conservative on cultural issues. In this paper, we propose a novel topic-factorized ideal point estimation model for a legislative voting network in a unified framework. First, we model the ideal points of legislators and bills for each topic instead of assigning them to a global one. Second, the generation of topics are guided by the voting matrix in addition to the text information contained in bills. A unified model that combines voting behavior modeling and topic modeling is presented, and an iterative learning algorithm is proposed to learn the topics of bills as well as the topic-factorized ideal points of legislators and bills. By comparing with the state-of-the-art ideal point estimation models, our method has a much better explanation power in terms of held-out log-likelihood and other measures. Besides, case studies show that the topic-factorized ideal points coincide with human intuition. Finally, we illustrate how to use these topic-factorized ideal points to predict voting results for unseen bills.