Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

"Recommendation": models, code, and papers

Detecting Mammals in UAV Images: Best Practices to address a substantially Imbalanced Dataset with Deep Learning

Jun 29, 2018
Benjamin Kellenberger, Diego Marcos, Devis Tuia

Knowledge over the number of animals in large wildlife reserves is a vital necessity for park rangers in their efforts to protect endangered species. Manual animal censuses are dangerous and expensive, hence Unmanned Aerial Vehicles (UAVs) with consumer level digital cameras are becoming a popular alternative tool to estimate livestock. Several works have been proposed that semi-automatically process UAV images to detect animals, of which some employ Convolutional Neural Networks (CNNs), a recent family of deep learning algorithms that proved very effective in object detection in large datasets from computer vision. However, the majority of works related to wildlife focuses only on small datasets (typically subsets of UAV campaigns), which might be detrimental when presented with the sheer scale of real study areas for large mammal census. Methods may yield thousands of false alarms in such cases. In this paper, we study how to scale CNNs to large wildlife census tasks and present a number of recommendations to train a CNN on a large UAV dataset. We further introduce novel evaluation protocols that are tailored to censuses and model suitability for subsequent human verification of detections. Using our recommendations, we are able to train a CNN reducing the number of false positives by an order of magnitude compared to previous state-of-the-art. Setting the requirements at 90% recall, our CNN allows to reduce the amount of data required for manual verification by three times, thus making it possible for rangers to screen all the data acquired efficiently and to detect almost all animals in the reserve automatically.

  Access Paper or Ask Questions

Data Science in Service of Performing Arts: Applying Machine Learning to Predicting Audience Preferences

Sep 30, 2016
Jacob Abernethy, Cyrus Anderson, Alex Chojnacki, Chengyu Dai, John Dryden, Eric Schwartz, Wenbo Shen, Jonathan Stroud, Laura Wendlandt, Sheng Yang, Daniel Zhang

Performing arts organizations aim to enrich their communities through the arts. To do this, they strive to match their performance offerings to the taste of those communities. Success relies on understanding audience preference and predicting their behavior. Similar to most e-commerce or digital entertainment firms, arts presenters need to recommend the right performance to the right customer at the right time. As part of the Michigan Data Science Team (MDST), we partnered with the University Musical Society (UMS), a non-profit performing arts presenter housed in the University of Michigan, Ann Arbor. We are providing UMS with analysis and business intelligence, utilizing historical individual-level sales data. We built a recommendation system based on collaborative filtering, gaining insights into the artistic preferences of customers, along with the similarities between performances. To better understand audience behavior, we used statistical methods from customer-base analysis. We characterized customer heterogeneity via segmentation, and we modeled customer cohorts to understand and predict ticket purchasing patterns. Finally, we combined statistical modeling with natural language processing (NLP) to explore the impact of wording in program descriptions. These ongoing efforts provide a platform to launch targeted marketing campaigns, helping UMS carry out its mission by allocating its resources more efficiently. Celebrating its 138th season, UMS is a 2014 recipient of the National Medal of Arts, and it continues to enrich communities by connecting world-renowned artists with diverse audiences, especially students in their formative years. We aim to contribute to that mission through data science and customer analytics.

* Presented at the Data For Good Exchange 2016 

  Access Paper or Ask Questions

AutoFIS: Automatic Feature Interaction Selection in Factorization Models for Click-Through Rate Prediction

Mar 26, 2020
Bin Liu, Chenxu Zhu, Guilin Li, Weinan Zhang, Jincai Lai, Ruiming Tang, Xiuqiang He, Zhenguo Li, Yong Yu

Learning effective feature interactions is crucial for click-through rate (CTR) prediction tasks in recommender systems. In most of the existing deep learning models, feature interactions are either manually designed or simply enumerated. However, enumerating all feature interactions brings large memory and computation cost. Even worse, useless interactions may introduce unnecessary noise and complicate the training process. In this work, we propose a two-stage algorithm called Automatic Feature Interaction Selection (AutoFIS). AutoFIS can automatically identify all the important feature interactions for factorization models with just the computational cost equivalent to training the target model to convergence. In the \emph{search stage}, instead of searching over a discrete set of candidate feature interactions, we relax the choices to be continuous by introducing the architecture parameters. By implementing a regularized optimizer over the architecture parameters, the model can automatically identify and remove the redundant feature interactions during the training process of the model. In the \emph{re-train stage}, we keep the architecture parameters serving as an attention unit to further boost the performance. Offline experiments on three large-scale datasets (two public benchmarks, one private) demonstrate that the proposed AutoFIS can significantly improve various FM based models. AutoFIS has been deployed onto the training platform of Huawei App Store recommendation service, where a 10-day online A/B test demonstrated that AutoFIS improved the DeepFM model by 20.3\% and 20.1\% in terms of CTR and CVR respectively.

  Access Paper or Ask Questions

Interpretable Predictions of Tree-based Ensembles via Actionable Feature Tweaking

Jun 20, 2017
Gabriele Tolomei, Fabrizio Silvestri, Andrew Haines, Mounia Lalmas

Machine-learned models are often described as "black boxes". In many real-world applications however, models may have to sacrifice predictive power in favour of human-interpretability. When this is the case, feature engineering becomes a crucial task, which requires significant and time-consuming human effort. Whilst some features are inherently static, representing properties that cannot be influenced (e.g., the age of an individual), others capture characteristics that could be adjusted (e.g., the daily amount of carbohydrates taken). Nonetheless, once a model is learned from the data, each prediction it makes on new instances is irreversible - assuming every instance to be a static point located in the chosen feature space. There are many circumstances however where it is important to understand (i) why a model outputs a certain prediction on a given instance, (ii) which adjustable features of that instance should be modified, and finally (iii) how to alter such a prediction when the mutated instance is input back to the model. In this paper, we present a technique that exploits the internals of a tree-based ensemble classifier to offer recommendations for transforming true negative instances into positively predicted ones. We demonstrate the validity of our approach using an online advertising application. First, we design a Random Forest classifier that effectively separates between two types of ads: low (negative) and high (positive) quality ads (instances). Then, we introduce an algorithm that provides recommendations that aim to transform a low quality ad (negative instance) into a high quality one (positive instance). Finally, we evaluate our approach on a subset of the active inventory of a large ad network, Yahoo Gemini.

* 10 pages, KDD 2017 

  Access Paper or Ask Questions

Perceive Your Users in Depth: Learning Universal User Representations from Multiple E-commerce Tasks

May 28, 2018
Yabo Ni, Dan Ou, Shichen Liu, Xiang Li, Wenwu Ou, Anxiang Zeng, Luo Si

Tasks such as search and recommendation have become increas- ingly important for E-commerce to deal with the information over- load problem. To meet the diverse needs of di erent users, person- alization plays an important role. In many large portals such as Taobao and Amazon, there are a bunch of di erent types of search and recommendation tasks operating simultaneously for person- alization. However, most of current techniques address each task separately. This is suboptimal as no information about users shared across di erent tasks. In this work, we propose to learn universal user representations across multiple tasks for more e ective personalization. In partic- ular, user behavior sequences (e.g., click, bookmark or purchase of products) are modeled by LSTM and attention mechanism by integrating all the corresponding content, behavior and temporal information. User representations are shared and learned in an end-to-end setting across multiple tasks. Bene ting from better information utilization of multiple tasks, the user representations are more e ective to re ect their interests and are more general to be transferred to new tasks. We refer this work as Deep User Perception Network (DUPN) and conduct an extensive set of o ine and online experiments. Across all tested ve di erent tasks, our DUPN consistently achieves better results by giving more e ective user representations. Moreover, we deploy DUPN in large scale operational tasks in Taobao. Detailed implementations, e.g., incre- mental model updating, are also provided to address the practical issues for the real world applications.

* 10 pages, accepted an oral paper in sigKDD2018(industry track) 

  Access Paper or Ask Questions

Toward a Robust Diversity-Based Model to Detect Changes of Context

Jan 08, 2016
Sylvain Castagnos, Amaury L 'Huillier, Anne Boyer

Being able to automatically and quickly understand the user context during a session is a main issue for recommender systems. As a first step toward achieving that goal, we propose a model that observes in real time the diversity brought by each item relatively to a short sequence of consultations, corresponding to the recent user history. Our model has a complexity in constant time, and is generic since it can apply to any type of items within an online service (e.g. profiles, products, music tracks) and any application domain (e-commerce, social network, music streaming), as long as we have partial item descriptions. The observation of the diversity level over time allows us to detect implicit changes. In the long term, we plan to characterize the context, i.e. to find common features among a contiguous sub-sequence of items between two changes of context determined by our model. This will allow us to make context-aware and privacy-preserving recommendations, to explain them to users. As this is an ongoing research, the first step consists here in studying the robustness of our model while detecting changes of context. In order to do so, we use a music corpus of 100 users and more than 210,000 consultations (number of songs played in the global history). We validate the relevancy of our detections by finding connections between changes of context and events, such as ends of session. Of course, these events are a subset of the possible changes of context, since there might be several contexts within a session. We altered the quality of our corpus in several manners, so as to test the performances of our model when confronted with sparsity and different types of items. The results show that our model is robust and constitutes a promising approach.

* 27th IEEE International Conference on Tools with Artificial Intelligence (ICTAI 2015), Nov 2015, Vietri sul Mare, Italy 

  Access Paper or Ask Questions

A Physician Advisory System for Chronic Heart Failure Management Based on Knowledge Patterns

Oct 25, 2016
Zhuo Chen, Kyle Marple, Elmer Salazar, Gopal Gupta, Lakshman Tamil

Management of chronic diseases such as heart failure, diabetes, and chronic obstructive pulmonary disease (COPD) is a major problem in health care. A standard approach that the medical community has devised to manage widely prevalent chronic diseases such as chronic heart failure (CHF) is to have a committee of experts develop guidelines that all physicians should follow. These guidelines typically consist of a series of complex rules that make recommendations based on a patient's information. Due to their complexity, often the guidelines are either ignored or not complied with at all, which can result in poor medical practices. It is not even clear whether it is humanly possible to follow these guidelines due to their length and complexity. In the case of CHF management, the guidelines run nearly 80 pages. In this paper we describe a physician-advisory system for CHF management that codes the entire set of clinical practice guidelines for CHF using answer set programming. Our approach is based on developing reasoning templates (that we call knowledge patterns) and using these patterns to systemically code the clinical guidelines for CHF as ASP rules. Use of the knowledge patterns greatly facilitates the development of our system. Given a patient's medical information, our system generates a recommendation for treatment just as a human physician would, using the guidelines. Our system will work even in the presence of incomplete information. Our work makes two contributions: (i) it shows that highly complex guidelines can be successfully coded as ASP rules, and (ii) it develops a series of knowledge patterns that facilitate the coding of knowledge expressed in a natural language and that can be used for other application domains. This paper is under consideration for acceptance in TPLP.

* Paper presented at the 32nd International Conference on Logic Programming (ICLP 2016), New York City, USA, 16-21 October 2016, 14 pages, LaTeX 

  Access Paper or Ask Questions

Modelling Student Behavior using Granular Large Scale Action Data from a MOOC

Aug 16, 2016
Steven Tang, Joshua C. Peterson, Zachary A. Pardos

Digital learning environments generate a precise record of the actions learners take as they interact with learning materials and complete exercises towards comprehension. With this high quantity of sequential data comes the potential to apply time series models to learn about underlying behavioral patterns and trends that characterize successful learning based on the granular record of student actions. There exist several methods for looking at longitudinal, sequential data like those recorded from learning environments. In the field of language modelling, traditional n-gram techniques and modern recurrent neural network (RNN) approaches have been applied to algorithmically find structure in language and predict the next word given the previous words in the sentence or paragraph as input. In this paper, we draw an analogy to this work by treating student sequences of resource views and interactions in a MOOC as the inputs and predicting students' next interaction as outputs. In this study, we train only on students who received a certificate of completion. In doing so, the model could potentially be used for recommendation of sequences eventually leading to success, as opposed to perpetuating unproductive behavior. Given that the MOOC used in our study had over 3,500 unique resources, predicting the exact resource that a student will interact with next might appear to be a difficult classification problem. We find that simply following the syllabus (built-in structure of the course) gives on average 23% accuracy in making this prediction, followed by the n-gram method with 70.4%, and RNN based methods with 72.2%. This research lays the ground work for recommendation in a MOOC and other digital learning environments where high volumes of sequential data exist.

* 15 pages, 7 tables, 3 figures 

  Access Paper or Ask Questions

Incorporating Wireless Communication Parameters into the E-Model Algorithm

Mar 05, 2021
Demóstenes Z. Rodríguez, Dick Carrillo Melgarejo, Miguel A. Ramírez, Pedro H. J. Nardelli, Sebastian Möller

Telecommunication service providers have to guarantee acceptable speech quality during a phone call to avoid a negative impact on the users' quality of experience. Currently, there are different speech quality assessment methods. ITU-T Recommendation G.107 describes the E-model algorithm, which is a computational model developed for network planning purposes focused on narrowband (NB) networks. Later, ITU-T Recommendations G.107.1 and G.107.2 were developed for wideband (WB) and fullband (FB) networks. These algorithms use different impairment factors, each one related to different speech communication steps. However, the NB, WB, and FB E-model algorithms do not consider wireless techniques used in these networks, such as Multiple-Input-Multiple-Output (MIMO) systems, which are used to improve the communication system robustness in the presence of different types of wireless channel degradation. In this context, the main objective of this study is to propose a general methodology to incorporate wireless network parameters into the NB and WB E-model algorithms. To accomplish this goal, MIMO and wireless channel parameters are incorporated into the E-model algorithms, specifically into the $I_{e,eff}$ and $I_{e,eff,WB}$ impairment factors. For performance validation, subjective tests were carried out, and the proposed methodology reached a Pearson correlation coefficient (PCC) and a root mean square error (RMSE) of $0.9732$ and $0.2351$, respectively. It is noteworthy that our proposed methodology does not affect the rest of the E-model input parameters, and it intends to be useful for wireless network planning in speech communication services.

* 18 pages 

  Access Paper or Ask Questions

Fairness-Aware Online Personalization

Sep 06, 2020
G Roshan Lal, Sahin Cem Geyik, Krishnaram Kenthapadi

Decision making in crucial applications such as lending, hiring, and college admissions has witnessed increasing use of algorithmic models and techniques as a result of a confluence of factors such as ubiquitous connectivity, ability to collect, aggregate, and process large amounts of fine-grained data using cloud computing, and ease of access to applying sophisticated machine learning models. Quite often, such applications are powered by search and recommendation systems, which in turn make use of personalized ranking algorithms. At the same time, there is increasing awareness about the ethical and legal challenges posed by the use of such data-driven systems. Researchers and practitioners from different disciplines have recently highlighted the potential for such systems to discriminate against certain population groups, due to biases in the datasets utilized for learning their underlying recommendation models. We present a study of fairness in online personalization settings involving the ranking of individuals. Starting from a fair warm-start machine-learned model, we first demonstrate that online personalization can cause the model to learn to act in an unfair manner if the user is biased in his/her responses. For this purpose, we construct a stylized model for generating training data with potentially biased features as well as potentially biased labels and quantify the extent of bias that is learned by the model when the user responds in a biased manner as in many real-world scenarios. We then formulate the problem of learning personalized models under fairness constraints and present a regularization based approach for mitigating biases in machine learning. We demonstrate the efficacy of our approach through extensive simulations with different parameter settings. Code:

* Accepted in RecSys 2020, FAccTRec Workshop: Responsible Recommendation 

  Access Paper or Ask Questions