An Unsupervised Aspect-Aware Recommendation Model with Explanation Text Generation

Review based recommendation utilizes both users’ rating records and the associated reviews for recommendation. Recently, with the rapid demand for explanations of recommendation results, reviews are used to train the encoder–decoder models for explanation text generation. As most of the reviews are general text without detailed evaluation, some researchers leveraged auxiliary information of users or items to enrich the generated explanation text. Nevertheless, the auxiliary data is not available in most scenarios and may suffer from data privacy problems. In this article, we argue that the reviews contain abundant semantic information to express the users’ feelings for various aspects of items, while these information are not fully explored in current explanation text generation task. To this end, we study how to generate more fine-grained explanation text in review based recommendation without any auxiliary data. Though the idea is simple, it is non-trivial since the aspect is hidden and unlabeled. Besides, it is also very challenging to inject aspect information for generating explanation text with noisy review input. To solve these challenges, we first leverage an advanced unsupervised neural aspect extraction model to learn the aspect-aware representation of each review sentence. Thus, users and items can be represented in the aspect space based on their historical associated reviews. After that, we detail how to better predict ratings and generate explanation text with the user and item representations in the aspect space. We further dynamically assign review sentences which contain larger proportion of aspect words with larger weights to control the text generation process, and jointly optimize rating prediction accuracy and explanation text generation quality with a multi-task learning framework. Finally, extensive experimental results on three real-world datasets demonstrate the superiority of our proposed model for both recommendation accuracy and explainability.

Self-Aware Contextual Behavior Analysis for Service Quality Assurance Over Social Networks

Social media allows people to share their ideologue through an efficient channel of communication. The social dialogues carry sentiment in expression regarding a particular social profile, trend, or topic. In our research, we have collected real-time user comments and feedbacks from Twitter portals of two food delivery services. This is followed by the extraction of the most prevalent contexts using natural language analytics. Further, our proposed algorithmic framework is used to generate a signed social network to analyze the product-centric behavioral sentiment. Analysis of sentiment with the fine-grained level about contexts gave a broader view to evaluate and perform contextual predictions. Customer behavior is analyzed, and the outcome is received in terms of positive and negative contexts. The results from our social behavioral model predicted the positive and negative contextual sentiments of customers, which can be further used to help in deciding future strategies and assuring service quality for better customer satisfaction.

Optimal Bounds for the k -cut Problem

In the k -cut problem, we want to find the lowest-weight set of edges whose deletion breaks a given (multi)graph into k connected components. Algorithms of Karger and Stein can solve this in roughly O ( n 2k ) time. However, lower bounds from conjectures about the k -clique problem imply that Ω ( n (1- o (1)) k ) time is likely needed. Recent results of Gupta, Lee, and Li have given new algorithms for general k -cut in n 1.98k + O(1) time, as well as specialized algorithms with better performance for certain classes of graphs (e.g., for small integer edge weights). In this work, we resolve the problem for general graphs. We show that the Contraction Algorithm of Karger outputs any fixed k -cut of weight α λ k with probability Ω k ( n - α k ), where λ k denotes the minimum k -cut weight. This also gives an extremal bound of O k ( n k ) on the number of minimum k -cuts and an algorithm to compute λ k with roughly n k polylog( n ) runtime. Both are tight up to lower-order factors, with the algorithmic lower bound assuming hardness of max-weight k -clique. The first main ingredient in our result is an extremal bound on the number of cuts of weight less than 2 λ k / k , using the Sunflower lemma. The second ingredient is a fine-grained analysis of how the graph shrinks—and how the average degree evolves—in the Karger process.

Personalized, Sequential, Attentive, Metric-Aware Product Search

The task of personalized product search aims at retrieving a ranked list of products given a user’s input query and his/her purchase history. To address this task, we propose the PSAM model, a Personalized, Sequential, Attentive and Metric-aware (PSAM) model, that learns the semantic representations of three different categories of entities, i.e., users, queries, and products, based on user sequential purchase historical data and the corresponding sequential queries. Specifically, a query-based attentive LSTM (QA-LSTM) model and an attention mechanism are designed to infer users dynamic embeddings, which is able to capture their short-term and long-term preferences. To obtain more fine-grained embeddings of the three categories of entities, a metric-aware objective is deployed in our model to force the inferred embeddings subject to the triangle inequality, which is a more realistic distance measurement for product search. Experiments conducted on four benchmark datasets show that our PSAM model significantly outperforms the state-of-the-art product search baselines in terms of effectiveness by up to 50.9% improvement under NDCG@20. Our visualization experiments further illustrate that the learned product embeddings are able to distinguish different types of products.

Incremental Group-Level Popularity Prediction in Online Social Networks

Predicting the popularity of web contents in online social networks is essential for many applications. However, existing works are usually under non-incremental settings. In other words, they have to rebuild models from scratch when new data occurs, which are inefficient in big data environments. It leads to an urgent need for incremental prediction, which can update previous results with new data and conduct prediction incrementally. Moreover, the promising direction of group-level popularity prediction has not been well treated, which explores fine-grained information while keeping a low cost. To this end, we identify the problem of incremental group-level popularity prediction, and propose a novel model IGPP to address it. We first predict the group-level popularity incrementally by exploiting the incremental CANDECOMP/PARAFCAC (CP) tensor decomposition algorithm. Then, to reduce the cumulative error by incremental prediction, we propose three strategies to restart the CP decomposition. To the best of our knowledge, this is the first work that identifies and solves the problem of incremental group-level popularity prediction. Extensive experimental results show significant improvements of the IGPP method over other works both in the prediction accuracy and the efficiency.

A Novel Hybrid Approach for Multi-Dimensional Data Anonymization for Apache Spark

Multi-dimensional data anonymization approaches (e.g., Mondrian) ensure more fine-grained data privacy by providing a different anonymization strategy applied for each attribute. Many variations of multi-dimensional anonymization have been implemented on different distributed processing platforms (e.g., MapReduce, Spark) to take advantage of their scalability and parallelism supports. According to our critical analysis on overheads, either existing iteration-based or recursion-based approaches do not provide effective mechanisms for creating the optimal number of and relative size of resilient distributed datasets (RDDs), thus heavily suffer from performance overheads. To solve this issue, we propose a novel hybrid approach for effectively implementing a multi-dimensional data anonymization strategy (e.g., Mondrian) that is scalable and provides high-performance. Our hybrid approach provides a mechanism to create far fewer RDDs and smaller size partitions attached to each RDD than existing approaches. This optimal RDD creation and operations approach is critical for many multi-dimensional data anonymization applications that create tremendous execution complexity. The new mechanism in our proposed hybrid approach can dramatically reduce the critical overheads involved in re-computation cost, shuffle operations, message exchange, and cache management.

Being Correct Is Not Enough: Efficient Verification Using Robust Linear Temporal Logic

While most approaches in formal methods address system correctness, ensuring robustness has remained a challenge. In this article, we present and study the logic rLTL, which provides a means to formally reason about both correctness and robustness in system design. Furthermore, we identify a large fragment of rLTL for which the verification problem can be efficiently solved, i.e., verification can be done by using an automaton, recognizing the behaviors described by the rLTL formula φ, of size at most O(3 |φ |), where |φ | is the length of φ. This result improves upon the previously known bound of O(5|φ |) for rLTL verification and is closer to the LTL bound of O(2|φ |). The usefulness of this fragment is demonstrated by a number of case studies showing its practical significance in terms of expressiveness, the ability to describe robustness, and the fine-grained information that rLTL brings to the process of system verification. Moreover, these advantages come at a low computational overhead with respect to LTL verification.

Jointly Predicting Future Content in Multiple Social Media Sites Based on Multi-task Learning

User-generated contents (UGC) in social media are the direct expression of users’ interests, preferences, and opinions. User behavior prediction based on UGC has increasingly been investigated in recent years. Compared to learning a person’s behavioral patterns in each social media site separately, jointly predicting user behavior in multiple social media sites and complementing each other (cross-site user behavior prediction) can be more accurate. However, cross-site user behavior prediction based on UGC is a challenging task due to the difficulty of cross-site data sampling, the complexity of UGC modeling, and uncertainty of knowledge sharing among different sites. For these problems, we propose a Cross-Site Multi-Task (CSMT) learning method to jointly predict user behavior in multiple social media sites. CSMT mainly derives from the hierarchical attention network and multi-task learning. Using this method, the UGC in each social media site can obtain fine-grained representations in terms of words, topics, posts, hashtags, and time slices as well as the relevances among them, and prediction tasks in different social media sites can be jointly implemented and complement each other. By utilizing two cross-site datasets sampled from Weibo, Douban, Facebook, and Twitter, we validate our method’s superiority on several classification metrics compared with existing related methods.

Towards Fine-Grained Online Adaptive Approximation Control for Dense SLAM on Embedded GPUs

Dense SLAM is an important application on an embedded environment. However, embedded platforms usually fail to provide enough computation resources for high-accuracy real-time dense SLAM, even with high-parallelism architecture such as GPUs. To tackle this problem, one solution is to design proper approximation techniques for dense SLAM on embedded GPUs. In this work, we propose two novel approximation techniques, critical data identification and redundant branch elimination. We also analyze the error characteristics of the other two techniques—loop skipping and thread approximation. Then, we propose SLaPP, an online adaptive approximation controller, which aims to control the error to be under an acceptable threshold. The evaluation shows SLaPP can achieve 2.0× performance speedup and 30% energy saving on average compared to the case without approximation.