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

Improved explanatory efficacy on human affect and workload through interactive process in artificial intelligence

Dec 13, 2019
Byung Hyung Kim, Seunghun Koh, Sejoon Huh, Sungho Jo

Despite recent advances in the field of explainable artificial intelligence systems, a concrete quantitative measure for evaluating the usability of such systems is nonexistent. Ensuring the success of an explanatory interface in interacting with users requires a cyclic, symbiotic relationship between human and artificial intelligence. We, therefore, propose explanatory efficacy, a novel metric for evaluating the strength of the cyclic relationship the interface exhibits. Furthermore, in a user study, we evaluated the perceived affect and workload and recorded the EEG signals of our participants as they interacted with our custom-built, iterative explanatory interface to build personalized recommendation systems. We found that systems for perceptually driven iterative tasks with greater explanatory efficacy are characterized by statistically significant hemispheric differences in neural signals, indicating the feasibility of neural correlates as a measure of explanatory efficacy. These findings are beneficial for researchers who aim to study the circular ecosystem of the human-artificial intelligence partnership.

  Access Paper or Ask Questions

Love Me, Love Me, Say (and Write!) that You Love Me: Enriching the WASABI Song Corpus with Lyrics Annotations

Dec 05, 2019
Michael Fell, Elena Cabrio, Elmahdi Korfed, Michel Buffa, Fabien Gandon

We present the WASABI Song Corpus, a large corpus of songs enriched with metadata extracted from music databases on the Web, and resulting from the processing of song lyrics and from audio analysis. More specifically, given that lyrics encode an important part of the semantics of a song, we focus here on the description of the methods we proposed to extract relevant information from the lyrics, such as their structure segmentation, their topics, the explicitness of the lyrics content, the salient passages of a song and the emotions conveyed. The creation of the resource is still ongoing: so far, the corpus contains 1.73M songs with lyrics (1.41M unique lyrics) annotated at different levels with the output of the above mentioned methods. Such corpus labels and the provided methods can be exploited by music search engines and music professionals (e.g. journalists, radio presenters) to better handle large collections of lyrics, allowing an intelligent browsing, categorization and segmentation recommendation of songs.

* 9 pages 

  Access Paper or Ask Questions

Node Injection Attacks on Graphs via Reinforcement Learning

Sep 14, 2019
Yiwei Sun, Suhang Wang, Xianfeng Tang, Tsung-Yu Hsieh, Vasant Honavar

Real-world graph applications, such as advertisements and product recommendations make profits based on accurately classify the label of the nodes. However, in such scenarios, there are high incentives for the adversaries to attack such graph to reduce the node classification performance. Previous work on graph adversarial attacks focus on modifying existing graph structures, which is infeasible in most real-world applications. In contrast, it is more practical to inject adversarial nodes into existing graphs, which can also potentially reduce the performance of the classifier. In this paper, we study the novel node injection poisoning attacks problem which aims to poison the graph. We describe a reinforcement learning based method, namely NIPA, to sequentially modify the adversarial information of the injected nodes. We report the results of experiments using several benchmark data sets that show the superior performance of the proposed method NIPA, relative to the existing state-of-the-art methods.

* Preprint, under review 

  Access Paper or Ask Questions

Split Q Learning: Reinforcement Learning with Two-Stream Rewards

Jun 21, 2019
Baihan Lin, Djallel Bouneffouf, Guillermo Cecchi

Drawing an inspiration from behavioral studies of human decision making, we propose here a general parametric framework for a reinforcement learning problem, which extends the standard Q-learning approach to incorporate a two-stream framework of reward processing with biases biologically associated with several neurological and psychiatric conditions, including Parkinson's and Alzheimer's diseases, attention-deficit/hyperactivity disorder (ADHD), addiction, and chronic pain. For AI community, the development of agents that react differently to different types of rewards can enable us to understand a wide spectrum of multi-agent interactions in complex real-world socioeconomic systems. Moreover, from the behavioral modeling perspective, our parametric framework can be viewed as a first step towards a unifying computational model capturing reward processing abnormalities across multiple mental conditions and user preferences in long-term recommendation systems.

* IJCAI 2019. arXiv admin note: substantial text overlap with arXiv:1706.02897 and arXiv:1906.11286 

  Access Paper or Ask Questions

The Scientific Method in the Science of Machine Learning

Apr 24, 2019
Jessica Zosa Forde, Michela Paganini

In the quest to align deep learning with the sciences to address calls for rigor, safety, and interpretability in machine learning systems, this contribution identifies key missing pieces: the stages of hypothesis formulation and testing, as well as statistical and systematic uncertainty estimation -- core tenets of the scientific method. This position paper discusses the ways in which contemporary science is conducted in other domains and identifies potentially useful practices. We present a case study from physics and describe how this field has promoted rigor through specific methodological practices, and provide recommendations on how machine learning researchers can adopt these practices into the research ecosystem. We argue that both domain-driven experiments and application-agnostic questions of the inner workings of fundamental building blocks of machine learning models ought to be examined with the tools of the scientific method, to ensure we not only understand effect, but also begin to understand cause, which is the raison d'\^{e}tre of science.

* 4 pages + 1 appendix. Presented at the ICLR 2019 Debugging Machine Learning Models workshop 

  Access Paper or Ask Questions

Compositional Verification for Autonomous Systems with Deep Learning Components

Oct 18, 2018
Corina S. Pasareanu, Divya Gopinath, Huafeng Yu

As autonomy becomes prevalent in many applications, ranging from recommendation systems to fully autonomous vehicles, there is an increased need to provide safety guarantees for such systems. The problem is difficult, as these are large, complex systems which operate in uncertain environments, requiring data-driven machine-learning components. However, learning techniques such as Deep Neural Networks, widely used today, are inherently unpredictable and lack the theoretical foundations to provide strong assurance guarantees. We present a compositional approach for the scalable, formal verification of autonomous systems that contain Deep Neural Network components. The approach uses assume-guarantee reasoning whereby {\em contracts}, encoding the input-output behavior of individual components, allow the designer to model and incorporate the behavior of the learning-enabled components working side-by-side with the other components. We illustrate the approach on an example taken from the autonomous vehicles domain.

  Access Paper or Ask Questions

Distilled Wasserstein Learning for Word Embedding and Topic Modeling

Sep 12, 2018
Hongteng Xu, Wenlin Wang, Wei Liu, Lawrence Carin

We propose a novel Wasserstein method with a distillation mechanism, yielding joint learning of word embeddings and topics. The proposed method is based on the fact that the Euclidean distance between word embeddings may be employed as the underlying distance in the Wasserstein topic model. The word distributions of topics, their optimal transports to the word distributions of documents, and the embeddings of words are learned in a unified framework. When learning the topic model, we leverage a distilled underlying distance matrix to update the topic distributions and smoothly calculate the corresponding optimal transports. Such a strategy provides the updating of word embeddings with robust guidance, improving the algorithmic convergence. As an application, we focus on patient admission records, in which the proposed method embeds the codes of diseases and procedures and learns the topics of admissions, obtaining superior performance on clinically-meaningful disease network construction, mortality prediction as a function of admission codes, and procedure recommendation.

  Access Paper or Ask Questions

Attaining the Unattainable? Reassessing Claims of Human Parity in Neural Machine Translation

Aug 30, 2018
Antonio Toral, Sheila Castilho, Ke Hu, Andy Way

We reassess a recent study (Hassan et al., 2018) that claimed that machine translation (MT) has reached human parity for the translation of news from Chinese into English, using pairwise ranking and considering three variables that were not taken into account in that previous study: the language in which the source side of the test set was originally written, the translation proficiency of the evaluators, and the provision of inter-sentential context. If we consider only original source text (i.e. not translated from another language, or translationese), then we find evidence showing that human parity has not been achieved. We compare the judgments of professional translators against those of non-experts and discover that those of the experts result in higher inter-annotator agreement and better discrimination between human and machine translations. In addition, we analyse the human translations of the test set and identify important translation issues. Finally, based on these findings, we provide a set of recommendations for future human evaluations of MT.

* WMT 2018 

  Access Paper or Ask Questions

MetaCon: Unified Predictive Segments System with Trillion Concept Meta-Learning

Mar 09, 2022
Keqian Li, Yifan Hu, Logan Palanisamy, Lisa Jones, Akshay Gupta, Jason Grigsby, Ili Selinger, Matt Gillingham, Fei Tan

Accurate understanding of users in terms of predicative segments play an essential role in the day to day operation of modern internet enterprises. Nevertheless, there are significant challenges that limit the quality of data, especially on long tail predictive tasks. In this work, we present MetaCon, our unified predicative segments system with scalable, trillion concepts meta learning that addresses these challenges. It builds on top of a flat concept representation that summarizes entities' heterogeneous digital footprint, jointly considers the entire spectrum of predicative tasks as a single learning task, and leverages principled meta learning approach with efficient first order meta-optimization procedure under a provable performance guarantee in order to solve the learning task. Experiments on both proprietary production datasets and public structured learning tasks demonstrate that MetaCon can lead to substantial improvements over state of the art recommendation and ranking approaches.

  Access Paper or Ask Questions

Comparison of Neural Network based Soft Computing Techniques for Electromagnetic Modeling of a Microstrip Patch Antenna

Sep 21, 2021
Yuvraj Singh Malhi, Navneet Gupta

This paper presents the comparison of various neural networks and algorithms based on accuracy, quickness, and consistency for antenna modelling. Using Nntool by MATLAB, 22 different combinations of networks and training algorithms are used to predict the dimensions of a rectangular microstrip antenna using dielectric constant, height of substrate, and frequency of operation as input. Comparison and characterization of networks is done based on accuracy, mean square error, and training time. Algorithms, on the other hand, are analyzed by their accuracy, speed, reliability, and smoothness in the training process. Finally, these results are analyzed, and recommendations are made for each neural network and algorithm based on uses, advantages, and disadvantages. For example, it is observed that Reduced Radial Bias network is the most accurate network and Scaled Conjugate Gradient is the most reliable algorithm for electromagnetic modelling. This paper will help a researcher find the optimum network and algorithm directly without doing time-taking experimentation.

* 10 pages (with smaller size as per conference submission guidelines), 9 figures, 4 tables. Submitted to SoCTA (Soft Computing: Theories and Applications) 2021 

  Access Paper or Ask Questions