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

Chrome logo Add to Chrome

Firefox logo Add to Firefox

"Topic": models, code, and papers

Fairness in Bio-inspired Optimization Research: A Prescription of Methodological Guidelines for Comparing Meta-heuristics

Apr 19, 2020
Antonio LaTorre, Daniel Molina, Eneko Osaba, Javier Del Ser, Francisco Herrera

Bio-inspired optimization (including Evolutionary Computation and Swarm Intelligence) is a growing research topic with many competitive bio-inspired algorithms being proposed every year. In such an active area, preparing a successful proposal of a new bio-inspired algorithm is not an easy task. Given the maturity of this research field, proposing a new optimization technique with innovative elements is no longer enough. Apart from the novelty, results reported by the authors should be proven to achieve a significant advance over previous outcomes from the state of the art. Unfortunately, not all new proposals deal with this requirement properly. Some of them fail to select an appropriate benchmark or reference algorithms to compare with. In other cases, the validation process carried out is not defined in a principled way (or is even not done at all). Consequently, the significance of the results presented in such studies cannot be guaranteed. In this work we review several recommendations in the literature and propose methodological guidelines to prepare a successful proposal, taking all these issues into account. We expect these guidelines to be useful not only for authors, but also for reviewers and editors along their assessment of new contributions to the field.

* 43 pages, 4 figures 

  Access Paper or Ask Questions

Learning Pose-invariant 3D Object Reconstruction from Single-view Images

Apr 03, 2020
Bo Peng, Wei Wang, Jing Dong, Tieniu Tan

Learning to reconstruct 3D shapes using 2D images is an active research topic, with benefits of not requiring expensive 3D data. However, most work in this direction requires multi-view images for each object instance as training supervision, which oftentimes does not apply in practice. In this paper, we relax the common multi-view assumption and explore a more challenging yet more realistic setup of learning 3D shape from only single-view images. The major difficulty lies in insufficient constraints that can be provided by single view images, which leads to the problem of pose entanglement in learned shape space. As a result, reconstructed shapes vary along input pose and have poor accuracy. We address this problem by taking a novel domain adaptation perspective, and propose an effective adversarial domain confusion method to learn pose-disentangled compact shape space. Experiments on single-view reconstruction show effectiveness in solving pose entanglement, and the proposed method achieves state-of-the-art reconstruction accuracy with high efficiency.

* under review, code available at 

  Access Paper or Ask Questions

PDE-NetGen 1.0: from symbolic PDE representations of physical processes to trainable neural network representations

Feb 03, 2020
Olivier Pannekoucke, Ronan Fablet

Bridging physics and deep learning is a topical challenge. While deep learning frameworks open avenues in physical science, the design of physically-consistent deep neural network architectures is an open issue. In the spirit of physics-informed NNs, PDE-NetGen package provides new means to automatically translate physical equations, given as PDEs, into neural network architectures. PDE-NetGen combines symbolic calculus and a neural network generator. The later exploits NN-based implementations of PDE solvers using Keras. With some knowledge of a problem, PDE-NetGen is a plug-and-play tool to generate physics-informed NN architectures. They provide computationally-efficient yet compact representations to address a variety of issues, including among others adjoint derivation, model calibration, forecasting, data assimilation as well as uncertainty quantification. As an illustration, the workflow is first presented for the 2D diffusion equation, then applied to the data-driven and physics-informed identification of uncertainty dynamics for the Burgers equation.

  Access Paper or Ask Questions

Deep Learning for MIR Tutorial

Jan 15, 2020
Alexander Schindler, Thomas Lidy, Sebastian Böck

Deep Learning has become state of the art in visual computing and continuously emerges into the Music Information Retrieval (MIR) and audio retrieval domain. In order to bring attention to this topic we propose an introductory tutorial on deep learning for MIR. Besides a general introduction to neural networks, the proposed tutorial covers a wide range of MIR relevant deep learning approaches. \textbf{Convolutional Neural Networks} are currently a de-facto standard for deep learning based audio retrieval. \textbf{Recurrent Neural Networks} have proven to be effective in onset detection tasks such as beat or audio-event detection. \textbf{Siamese Networks} have been shown effective in learning audio representations and distance functions specific for music similarity retrieval. We will incorporate both academic and industrial points of view into the tutorial. Accompanying the tutorial, we will create a Github repository for the content presented at the tutorial as well as references to state of the art work and literature for further reading. This repository will remain public after the conference.

* This is a description of a tutorial held at the 19th International Society for Music Information Retrieval Conference, ISMIR 2018, Paris, France, September 23-27, 2018. 2018 

  Access Paper or Ask Questions

Introducing the Robot Vulnerability Database (RVD)

Dec 24, 2019
Víctor Mayoral Vilches, Lander Usategui San Juan, Bernhard Dieber, Unai Ayucar Carbajo, Endika Gil-Uriarte

Cybersecurity in robotics is an emerging topic that has gained significant traction. Researchers have demonstrated some of the potentials and effects of cyber attacks on robots lately. This implies safety related adverse consequences causing human harm, death or lead to significant integrity loss clearly overcoming the privacy concerns in classical IT world. In cybersecurity research, the use of vulnerability databases is a very reliable tool to responsibly disclose vulnerabilities in software products and raise willingness of vendors to address these issues. In this paper we argue, that existing vulnerability databases are of insufficient information density and show some biased content with respect to vulnerabilities in robots. This paper presents the Robot Vulnerability Database (RVD), a directory for responsible disclosure of bugs, weaknesses and vulnerabilities in robots. This article aims to describe the design and process as well as the associated disclosure policy behind RVD. Furthermore the authors present preliminary selected vulnerabilities already contained in RVD and call to the robotics and security communities for contribution to the endeavour of eliminating zero-day vulnerabilities in robotics.

  Access Paper or Ask Questions

CROWN: Conversational Passage Ranking by Reasoning over Word Networks

Nov 11, 2019
Magdalena Kaiser, Rishiraj Saha Roy, Gerhard Weikum

Information needs around a topic cannot be satisfied in a single turn; users typically ask follow-up questions referring to the same theme and a system must be capable of understanding the conversational context of a request to retrieve correct answers. In this paper, we present our submission to the TREC Conversational Assistance Track 2019, in which such a conversational setting is explored. We propose a simple unsupervised method for conversational passage ranking by formulating the passage score for a query as a combination of similarity and coherence. To be specific, passages are preferred that contain words semantically similar to the words used in the question, and where such words appear close by. We built a word-proximity network (WPN) from a large corpus, where words are nodes and there is an edge between two nodes if they co-occur in the same passages in a statistically significant way, within a context window. Our approach, named CROWN, improved nDCG scores over a provided Indri baseline on the CAsT training data. On the evaluation data for CAsT, our best run submission achieved above-average performance with respect to [email protected] and [email protected]

* TREC 2019 
* TREC 2019, 13 pages 

  Access Paper or Ask Questions

Look before you Hop: Conversational Question Answering over Knowledge Graphs Using Judicious Context Expansion

Nov 05, 2019
Philipp Christmann, Rishiraj Saha Roy, Abdalghani Abujabal, Jyotsna Singh, Gerhard Weikum

Fact-centric information needs are rarely one-shot; users typically ask follow-up questions to explore a topic. In such a conversational setting, the user's inputs are often incomplete, with entities or predicates left out, and ungrammatical phrases. This poses a huge challenge to question answering (QA) systems that typically rely on cues in full-fledged interrogative sentences. As a solution, we develop CONVEX: an unsupervised method that can answer incomplete questions over a knowledge graph (KG) by maintaining conversation context using entities and predicates seen so far and automatically inferring missing or ambiguous pieces for follow-up questions. The core of our method is a graph exploration algorithm that judiciously expands a frontier to find candidate answers for the current question. To evaluate CONVEX, we release ConvQuestions, a crowdsourced benchmark with 11,200 distinct conversations from five different domains. We show that CONVEX: (i) adds conversational support to any stand-alone QA system, and (ii) outperforms state-of-the-art baselines and question completion strategies.

* CIKM 2019 
* CIKM 2019 Long Paper, 10 pages 

  Access Paper or Ask Questions

Multiple Sample Clustering

Oct 24, 2019
Xiang Wang, Tie Liu

The clustering algorithms that view each object data as a single sample drawn from a certain distribution, Gaussian distribution, for example, has been a hot topic for decades. Many clustering algorithms: such as k-means and spectral clustering are proposed based on the single sample assumption. However, in real life, each input object can usually be the multiple samples drawn from a certain hidden distribution. The traditional clustering algorithms cannot handle such a situation. This calls for the multiple sample clustering algorithm. But the traditional multiple sample clustering algorithms can only handle scalar samples or samples from Gaussian distribution. This constrains the application field of multiple sample clustering algorithms. In this paper, we purpose a general framework for multiple sample clustering. Various algorithms can be generated by this framework. We apply two specific cases of this framework: Wasserstein distance version and Bhattacharyya distance version on both synthetic data and stock price data. The simulation results show that the sufficient statistic can greatly improve the clustering accuracy and stability.

* 17 pages, 11 figures 

  Access Paper or Ask Questions