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

Adviser Networks: Learning What Question to Ask for Human-In-The-Loop Viewpoint Estimation

Oct 25, 2018
Mohamed El Banani, Jason J. Corso

Humans have an unparalleled visual intelligence and can overcome visual ambiguities that machines currently cannot. Recent works have shown that incorporating guidance from humans during inference for monocular viewpoint-estimation can help overcome difficult cases in which the computer-alone would have otherwise failed. These hybrid intelligence approaches are hence gaining traction. However, deciding what question to ask the human at inference time remains an unknown for these problems. We address this question by formulating it as an Adviser Problem: can we learn a mapping from the input to a specific question to ask the human to maximize the expected positive impact to the overall task? We formulate a solution to the adviser problem for viewpoint estimation using a deep network where the question asks for the location of a keypoint in the input image. We show that by using the Adviser Network's recommendations, the model and the human outperforms the previous hybrid-intelligence state-of-the-art by 3.7%, and the computer-only state-of-the-art by 5.28% absolute.

* 15 pages, 3 figures. Updated Acknowledgment 

  Access Paper or Ask Questions

Adversarial Training of Word2Vec for Basket Completion

May 22, 2018
Ugo Tanielian, Mike Gartrell, Flavian Vasile

In recent years, the Word2Vec model trained with the Negative Sampling loss function has shown state-of-the-art results in a number of machine learning tasks, including language modeling tasks, such as word analogy and word similarity, and in recommendation tasks, through Prod2Vec, an extension that applies to modeling user shopping activity and user preferences. Several methods that aim to improve upon the standard Negative Sampling loss have been proposed. In our paper we pursue more sophisticated Negative Sampling, by leveraging ideas from the field of Generative Adversarial Networks (GANs), and propose Adversarial Negative Sampling. We build upon the recent progress made in stabilizing the training objective of GANs in the discrete data setting, and introduce a new GAN-Word2Vec model.We evaluate our model on the task of basket completion, and show significant improvements in performance over Word2Vec trained using standard loss functions, including Noise Contrastive Estimation and Negative Sampling.

* 5 pages 

  Access Paper or Ask Questions

Cellular Automaton Based Simulation of Large Pedestrian Facilities - A Case Study on the Staten Island Ferry Terminals

Sep 11, 2017
Luca Crociani, Gregor Lämmel, H. Joon Park, Giuseppe Vizzari

Current metropolises largely depend on a functioning transport infrastructure and the increasing demand can only be satisfied by a well organized mass transit. One example for a crucial mass transit system is New York City's Staten Island Ferry, connecting the two boroughs of Staten Island and Manhattan with a regular passenger service. Today's demand already exceeds 2500 passengers for a single cycle during peek hours, and future projections suggest that it will further increase. One way to appraise how the system will cope with future demand is by simulation. This contribution proposes an integrated simulation approach to evaluate the system performance with respect to future demand. The simulation relies on a multiscale modeling approach where the terminal buildings are simulated by a microscopic and quantitatively valid cellular automata (CA) and the journeys of the ferries themselves are modeled by a mesoscopic queue simulation approach. Based on the simulation results recommendations with respect to the future demand are given.

* 96th Transportation Research Board annual meeting, Washington, January 2017 

  Access Paper or Ask Questions

Efficient Rectangular Maximal-Volume Algorithm for Rating Elicitation in Collaborative Filtering

Oct 16, 2016
Alexander Fonarev, Alexander Mikhalev, Pavel Serdyukov, Gleb Gusev, Ivan Oseledets

Cold start problem in Collaborative Filtering can be solved by asking new users to rate a small seed set of representative items or by asking representative users to rate a new item. The question is how to build a seed set that can give enough preference information for making good recommendations. One of the most successful approaches, called Representative Based Matrix Factorization, is based on Maxvol algorithm. Unfortunately, this approach has one important limitation --- a seed set of a particular size requires a rating matrix factorization of fixed rank that should coincide with that size. This is not necessarily optimal in the general case. In the current paper, we introduce a fast algorithm for an analytical generalization of this approach that we call Rectangular Maxvol. It allows the rank of factorization to be lower than the required size of the seed set. Moreover, the paper includes the theoretical analysis of the method's error, the complexity analysis of the existing methods and the comparison to the state-of-the-art approaches.

* IEEE International Conference on Data Mining (ICDM) 2016 

  Access Paper or Ask Questions

LB2CO: A Semantic Ontology Framework for B2C eCommerce Transaction on the Internet

Jan 05, 2014
Adeyinka K Akanbi

Business ontology can enhance the successful development of complex enterprise system; this is being achieved through knowledge sharing and the ease of communication between every entity in the domain. Through human semantic interaction with the web resources, machines to interpret the data published in a machine interpretable form under web. However, the theoretical practice of business ontology in eCommerce domain is quite a few especially in the section of electronic transaction, and the various techniques used to obtain efficient communication across spheres are error prone and are not always guaranteed to be efficient in obtaining desired result due to poor semantic integration between entities. To overcome the poor semantic integration this research focuses on proposed ontology called LB2CO, which combines the framework of IDEF5 & SNAP as an analysis tool, for automated recommendation of product and services and create effective ontological framework for B2C transaction & communication across different business domains that facilitates the interoperability & integration of B2C transactions over the web.

* International Journal of Research in Computer Science, 4 (1): pp. 1-9, January 2014 
* 9 Pages, 7 figures, Research Paper 

  Access Paper or Ask Questions

Multi-Domain Collaborative Filtering

Mar 15, 2012
Yu Zhang, Bin Cao, Dit-Yan Yeung

Collaborative filtering is an effective recommendation approach in which the preference of a user on an item is predicted based on the preferences of other users with similar interests. A big challenge in using collaborative filtering methods is the data sparsity problem which often arises because each user typically only rates very few items and hence the rating matrix is extremely sparse. In this paper, we address this problem by considering multiple collaborative filtering tasks in different domains simultaneously and exploiting the relationships between domains. We refer to it as a multi-domain collaborative filtering (MCF) problem. To solve the MCF problem, we propose a probabilistic framework which uses probabilistic matrix factorization to model the rating problem in each domain and allows the knowledge to be adaptively transferred across different domains by automatically learning the correlation between domains. We also introduce the link function for different domains to correct their biases. Experiments conducted on several real-world applications demonstrate the effectiveness of our methods when compared with some representative methods.

* Appears in Proceedings of the Twenty-Sixth Conference on Uncertainty in Artificial Intelligence (UAI2010) 

  Access Paper or Ask Questions

Intersectionality Goes Analytical: Taming Combinatorial Explosion Through Type Abstraction

Jan 25, 2022
Margaret Burnett, Martin Erwig, Abrar Fallatah, Christopher Bogart, Anita Sarma

HCI researchers' and practitioners' awareness of intersectionality has been expanding, producing knowledge, recommendations, and prototypes for supporting intersectional populations. However, doing intersectional HCI work is uniquely expensive: it leads to a combinatorial explosion of empirical work (expense 1), and little of the work on one intersectional population can be leveraged to serve another (expense 2). In this paper, we explain how representations employed by certain analytical design methods correspond to type abstractions, and use that correspondence to identify a (de)compositional model in which a population's diverse identity properties can be joined and split. We formally prove the model's correctness, and show how it enables HCI designers to harness existing analytical HCI methods for use on new intersectional populations of interest. We illustrate through four design use-cases, how the model can reduce the amount of expense 1 and enable designers to leverage prior work to new intersectional populations, addressing expense 2.

  Access Paper or Ask Questions

On the Complementarity of Data Selection and Fine Tuning for Domain Adaptation

Sep 15, 2021
Dan Iter, David Grangier

Domain adaptation of neural networks commonly relies on three training phases: pretraining, selected data training and then fine tuning. Data selection improves target domain generalization by training further on pretraining data identified by relying on a small sample of target domain data. This work examines the benefit of data selection for language modeling and machine translation. Our experiments assess the complementarity of selection with fine tuning and result in practical recommendations: (i) selected data must be similar to the fine-tuning domain but not so much as to erode the complementary effect of fine-tuning; (ii) there is a trade-off between selecting little data for fast but limited progress or much data for slow but long lasting progress; (iii) data selection can be applied early during pretraining, with performance gains comparable to long pretraining session; (iv) data selection from domain classifiers is often more effective than the popular contrastive data selection method.

  Access Paper or Ask Questions

Multi-Granularity Network with Modal Attention for Dense Affective Understanding

Jun 18, 2021
Baoming Yan, Lin Wang, Ke Gao, Bo Gao, Xiao Liu, Chao Ban, Jiang Yang, Xiaobo Li

Video affective understanding, which aims to predict the evoked expressions by the video content, is desired for video creation and recommendation. In the recent EEV challenge, a dense affective understanding task is proposed and requires frame-level affective prediction. In this paper, we propose a multi-granularity network with modal attention (MGN-MA), which employs multi-granularity features for better description of the target frame. Specifically, the multi-granularity features could be divided into frame-level, clips-level and video-level features, which corresponds to visual-salient content, semantic-context and video theme information. Then the modal attention fusion module is designed to fuse the multi-granularity features and emphasize more affection-relevant modals. Finally, the fused feature is fed into a Mixtures Of Experts (MOE) classifier to predict the expressions. Further employing model-ensemble post-processing, the proposed method achieves the correlation score of 0.02292 in the EEV challenge.

* Oral presentation at AUVi Workshop - CVPR 2021 

  Access Paper or Ask Questions

On the Ethical Limits of Natural Language Processing on Legal Text

May 08, 2021
Dimitrios Tsarapatsanis, Nikolaos Aletras

Natural language processing (NLP) methods for analyzing legal text offer legal scholars and practitioners a range of tools allowing to empirically analyze law on a large scale. However, researchers seem to struggle when it comes to identifying ethical limits to using natural language processing (NLP) systems for acquiring genuine insights both about the law and the systems' predictive capacity. In this paper we set out a number of ways in which to think systematically about such issues. We place emphasis on three crucial normative parameters which have, to the best of our knowledge, been underestimated by current debates: (a) the importance of academic freedom, (b) the existence of a wide diversity of legal and ethical norms domestically but even more so internationally and (c) the threat of moralism in research related to computational law. For each of these three parameters we provide specific recommendations for the legal NLP community. Our discussion is structured around the study of a real-life scenario that has prompted recent debate in the legal NLP research community.

* Accepted at ACL Findings 2021 

  Access Paper or Ask Questions