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

Shortcut Learning in Deep Neural Networks

Apr 16, 2020
Robert Geirhos, Jörn-Henrik Jacobsen, Claudio Michaelis, Richard Zemel, Wieland Brendel, Matthias Bethge, Felix A. Wichmann

Deep learning has triggered the current rise of artificial intelligence and is the workhorse of today's machine intelligence. Numerous success stories have rapidly spread all over science, industry and society, but its limitations have only recently come into focus. In this perspective we seek to distil how many of deep learning's problem can be seen as different symptoms of the same underlying problem: shortcut learning. Shortcuts are decision rules that perform well on standard benchmarks but fail to transfer to more challenging testing conditions, such as real-world scenarios. Related issues are known in Comparative Psychology, Education and Linguistics, suggesting that shortcut learning may be a common characteristic of learning systems, biological and artificial alike. Based on these observations, we develop a set of recommendations for model interpretation and benchmarking, highlighting recent advances in machine learning to improve robustness and transferability from the lab to real-world applications.

* perspective article 

  Access Paper or Ask Questions

Do you comply with AI? -- Personalized explanations of learning algorithms and their impact on employees' compliance behavior

Feb 20, 2020
NIklas Kuhl, Jodie Lobana, Christian Meske

Machine Learning algorithms are technological key enablers for artificial intelligence (AI). Due to the inherent complexity, these learning algorithms represent black boxes and are difficult to comprehend, therefore influencing compliance behavior. Hence, compliance with the recommendations of such artifacts, which can impact employees' task performance significantly, is still subject to research - and personalization of AI explanations seems to be a promising concept in this regard. In our work, we hypothesize that, based on varying backgrounds like training, domain knowledge and demographic characteristics, individuals have different understandings and hence mental models about the learning algorithm. Personalization of AI explanations, related to the individuals' mental models, may thus be an instrument to affect compliance and therefore employee task performance. Our preliminary results already indicate the importance of personalized explanations in industry settings and emphasize the importance of this research endeavor.

* Fortieth International Conference on Information Systems (ICIS) 2019, Munich, Germany. All Authors contributed equally in shared first authorship 

  Access Paper or Ask Questions

AutoML using Metadata Language Embeddings

Oct 08, 2019
Iddo Drori, Lu Liu, Yi Nian, Sharath C. Koorathota, Jie S. Li, Antonio Khalil Moretti, Juliana Freire, Madeleine Udell

As a human choosing a supervised learning algorithm, it is natural to begin by reading a text description of the dataset and documentation for the algorithms you might use. We demonstrate that the same idea improves the performance of automated machine learning methods. We use language embeddings from modern NLP to improve state-of-the-art AutoML systems by augmenting their recommendations with vector embeddings of datasets and of algorithms. We use these embeddings in a neural architecture to learn the distance between best-performing pipelines. The resulting (meta-)AutoML framework improves on the performance of existing AutoML frameworks. Our zero-shot AutoML system using dataset metadata embeddings provides good solutions instantaneously, running in under one second of computation. Performance is competitive with AutoML systems OBOE, AutoSklearn, AlphaD3M, and TPOT when each framework is allocated a minute of computation. We make our data, models, and code publicly available.

* NeurIPS Workshop on Meta-Learning, 2019 

  Access Paper or Ask Questions

Collaborative Filtering via High-Dimensional Regression

Apr 30, 2019
Harald Steck

While the SLIM approach obtained high ranking-accuracy in many experiments in the literature, it is also known for its high computational cost of learning its parameters from data. For this reason, we focus in this paper on variants of high-dimensional regression problems that have closed-form solutions. Moreover, we motivate a re-scaling rather than a re-weighting approach for dealing with biases regarding item-popularities in the data. We also discuss properties of the sparse solution, and outline a computationally efficient approximation. In experiments on three publicly available data sets, we observed not only extremely reduced training times, but also significantly improved ranking accuracy compared to SLIM. Surprisingly, various state-of-the-art models, including deep non-linear autoencoders, were also outperformed on two of the three data sets in our experiments, in particular for recommendations with highly personalized relevance.

* 10 pages 

  Access Paper or Ask Questions

Expeditious Generation of Knowledge Graph Embeddings

Mar 21, 2018
Tommaso Soru, Stefano Ruberto, Diego Moussallem, Edgard Marx, Diego Esteves, Axel-Cyrille Ngonga Ngomo

Knowledge Graph Embedding methods aim at representing entities and relations in a knowledge base as points or vectors in a continuous vector space. Several approaches using embeddings have shown promising results on tasks such as link prediction, entity recommendation, question answering, and triplet classification. However, only a few methods can compute low-dimensional embeddings of very large knowledge bases. In this paper, we propose KG2Vec, a novel approach to Knowledge Graph Embedding based on the skip-gram model. Instead of using a predefined scoring function, we learn it relying on Long Short-Term Memories. We evaluated the goodness of our embeddings on knowledge graph completion and show that KG2Vec is comparable to the quality of the scalable state-of-the-art approaches and can process large graphs by parsing more than a hundred million triples in less than 6 hours on common hardware.

* Submitted, 6 pages 

  Access Paper or Ask Questions

Tips, guidelines and tools for managing multi-label datasets: the mldr.datasets R package and the Cometa data repository

Feb 10, 2018
Francisco Charte, Antonio J. Rivera, David Charte, María J. del Jesus, Francisco Herrera

New proposals in the field of multi-label learning algorithms have been growing in number steadily over the last few years. The experimentation associated with each of them always goes through the same phases: selection of datasets, partitioning, training, analysis of results and, finally, comparison with existing methods. This last step is often hampered since it involves using exactly the same datasets, partitioned in the same way and using the same validation strategy. In this paper we present a set of tools whose objective is to facilitate the management of multi-label datasets, aiming to standardize the experimentation procedure. The two main tools are an R package, mldr.datasets, and a web repository with datasets, Cometa. Together, these tools will simplify the collection of datasets, their partitioning, documentation and export to multiple formats, among other functions. Some tips, recommendations and guidelines for a good experimental analysis of multi-label methods are also presented.

  Access Paper or Ask Questions

An Influence-Receptivity Model for Topic based Information Cascades

Sep 06, 2017
Ming Yu, Varun Gupta, Mladen Kolar

We consider the problem of estimating the latent structure of a social network based on observational data on information diffusion processes, or {\it cascades}. Here for a given cascade, we only observe the time a node/agent is infected but not the source of infection. Existing literature has focused on estimating network diffusion matrix without any underlying assumptions on the structure of the network. We propose a novel model for inferring network diffusion matrix based on the intuition that an information datum is more likely to propagate among two nodes if they are interested in similar topics, which are common with the information. In particular, our model endows each node with an influence vector (how authoritative they are on each topic) and a receptivity vector (how susceptible they are on each topic). We show how this node-topic structure can be estimated from observed cascades. The estimated model can be used to build recommendation system based on the receptivity vectors, as well as for marketing based on the influence vectors.

  Access Paper or Ask Questions

User Intent Classification using Memory Networks: A Comparative Analysis for a Limited Data Scenario

Jun 19, 2017
Arjun Bhardwaj, Alexander Rudnicky

In this report, we provide a comparative analysis of different techniques for user intent classification towards the task of app recommendation. We analyse the performance of different models and architectures for multi-label classification over a dataset with a relative large number of classes and only a handful examples of each class. We focus, in particular, on memory network architectures, and compare how well the different versions perform under the task constraints. Since the classifier is meant to serve as a module in a practical dialog system, it needs to be able to work with limited training data and incorporate new data on the fly. We devise a 1-shot learning task to test the models under the above constraint. We conclude that relatively simple versions of memory networks perform better than other approaches. Although, for tasks with very limited data, simple non-parametric methods perform comparably, without needing the extra training data.

  Access Paper or Ask Questions

Supervised Typing of Big Graphs using Semantic Embeddings

Mar 22, 2017
Mayank Kejriwal, Pedro Szekely

We propose a supervised algorithm for generating type embeddings in the same semantic vector space as a given set of entity embeddings. The algorithm is agnostic to the derivation of the underlying entity embeddings. It does not require any manual feature engineering, generalizes well to hundreds of types and achieves near-linear scaling on Big Graphs containing many millions of triples and instances by virtue of an incremental execution. We demonstrate the utility of the embeddings on a type recommendation task, outperforming a non-parametric feature-agnostic baseline while achieving 15x speedup and near-constant memory usage on a full partition of DBpedia. Using state-of-the-art visualization, we illustrate the agreement of our extensionally derived DBpedia type embeddings with the manually curated domain ontology. Finally, we use the embeddings to probabilistically cluster about 4 million DBpedia instances into 415 types in the DBpedia ontology.

* 6 pages, to be published in Semantic Big Data Workshop at ACM, SIGMOD 2017; extended version in preparation for Open Journal of Semantic Web (OJSW) 

  Access Paper or Ask Questions

Collaboratively Learning Preferences from Ordinal Data

Jun 26, 2015
Sewoong Oh, Kiran K. Thekumparampil, Jiaming Xu

In applications such as recommendation systems and revenue management, it is important to predict preferences on items that have not been seen by a user or predict outcomes of comparisons among those that have never been compared. A popular discrete choice model of multinomial logit model captures the structure of the hidden preferences with a low-rank matrix. In order to predict the preferences, we want to learn the underlying model from noisy observations of the low-rank matrix, collected as revealed preferences in various forms of ordinal data. A natural approach to learn such a model is to solve a convex relaxation of nuclear norm minimization. We present the convex relaxation approach in two contexts of interest: collaborative ranking and bundled choice modeling. In both cases, we show that the convex relaxation is minimax optimal. We prove an upper bound on the resulting error with finite samples, and provide a matching information-theoretic lower bound.

* 38 pages 2 figures 

  Access Paper or Ask Questions