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

Data-driven preference learning methods for value-driven multiple criteria sorting with interacting criteria

May 21, 2019
Jiapeng Liu, Milosz Kadzinski, Xiuwu Liao, Xiaoxin Mao

The learning of predictive models for data-driven decision support has been a prevalent topic in many fields. However, construction of models that would capture interactions among input variables is a challenging task. In this paper, we present a new preference learning approach for multiple criteria sorting with potentially interacting criteria. It employs an additive piecewise-linear value function as the basic preference model, which is augmented with components for handling the interactions. To construct such a model from a given set of assignment examples concerning reference alternatives, we develop a convex quadratic programming model. Since its complexity does not depend on the number of training samples, the proposed approach is capable for dealing with data-intensive tasks. To improve the generalization of the constructed model on new instances and to overcome the problem of over-fitting, we employ the regularization techniques. We also propose a few novel methods for classifying non-reference alternatives in order to enhance the applicability of our approach to different datasets. The practical usefulness of the proposed method is demonstrated on a problem of parametric evaluation of research units, whereas its predictive performance is studied on several monotone learning datasets. The experimental results indicate that our approach compares favourably with the classical UTADIS method and the Choquet integral-based sorting model.

  Access Paper or Ask Questions

Arena: A General Evaluation Platform and Building Toolkit for Multi-Agent Intelligence

May 17, 2019
Yuhang Song, Jianyi Wang, Thomas Lukasiewicz, Zhenghua Xu, Mai Xu, Zihan Ding, Lianlong Wu

Learning agents that are not only capable of taking tests but also innovating is becoming the next hot topic in AI. One of the most promising paths towards this vision is multi-agent learning, where agents act as the environment for each other, and improving each agent means proposing new problems for the others. However, existing evaluation platforms are either not compatible with multi-agent settings, or limited to a specific game. That is, there is not yet a general evaluation platform for research on multi-agent intelligence. To this end, we introduce Arena, a general evaluation platform for multi-agent intelligence with \NumGames games of diverse logic and representations. Furthermore, multi-agent intelligence is still at the stage where many problems remain unexplored. Thus, we provide a building toolkit for researchers to invent and build novel multi-agent problems from the provided game set with little efforts. Finally, we provide python implementations of five state-of-the-art deep multi-agent reinforcement learning baselines. Along with the baseline implementations, we release a set of 100 best agents/teams that we can train with different training schemes for each game, as the base for evaluating agents with population performance, so that the research community can perform comparisons under a stable and uniform standard.

  Access Paper or Ask Questions

Episodic Training for Domain Generalization

Jan 31, 2019
Da Li, Jianshu Zhang, Yongxin Yang, Cong Liu, Yi-Zhe Song, Timothy M. Hospedales

Domain generalization (DG) is the challenging and topical problem of learning models that generalize to novel testing domain with different statistics than a set of known training domains. The simple approach of aggregating data from all source domains and training a single deep neural network end-to-end on all the data provides a surprisingly strong baseline that surpasses many prior published methods. In this paper we build on this strong baseline by designing an episodic training procedure that trains a single deep network in a way that exposes it to the domain shift that characterises a novel domain at runtime. Specifically, we decompose a deep network into feature extractor and classifier components, and then train each component by simulating it interacting with a partner who is badly tuned for the current domain. This makes both components more robust, ultimately leading to our networks producing state-of-the-art performance on three DG benchmarks. As a demonstration, we consider the pervasive workflow of using an ImageNet trained CNN as a fixed feature extractor for downstream recognition tasks. Using the Visual Decathlon benchmark, we demonstrate that our episodic-DG training improves the performance of such a general purpose feature extractor by explicitly training it for robustness to novel problems. This provides the largest-scale demonstration of heterogeneous DG to date.

* technical report 

  Access Paper or Ask Questions

A Survey on Data Collection for Machine Learning: a Big Data - AI Integration Perspective

Nov 08, 2018
Yuji Roh, Geon Heo, Steven Euijong Whang

Data collection is a major bottleneck in machine learning and an active research topic in multiple communities. There are largely two reasons data collection has recently become a critical issue. First, as machine learning is becoming more widely-used, we are seeing new applications that do not necessarily have enough labeled data. Second, unlike traditional machine learning where feature engineering is the bottleneck, deep learning techniques automatically generate features, but instead require large amounts of labeled data. Interestingly, recent research in data collection comes not only from the machine learning, natural language, and computer vision communities, but also from the data management community due to the importance of handling large amounts of data. In this survey, we perform a comprehensive study of data collection from a data management point of view. Data collection largely consists of data acquisition, data labeling, and improvement of existing data or models. We provide a research landscape of these operations, provide guidelines on which technique to use when, and identify interesting research challenges. The integration of machine learning and data management for data collection is part of a larger trend of Big data and Artificial Intelligence (AI) integration and opens many opportunities for new research.

* 19 pages 

  Access Paper or Ask Questions

A Survey of Multi-View Representation Learning

Oct 24, 2018
Yingming Li, Ming Yang, Zhongfei Zhang

Recently, multi-view representation learning has become a rapidly growing direction in machine learning and data mining areas. This paper introduces two categories for multi-view representation learning: multi-view representation alignment and multi-view representation fusion. Consequently, we first review the representative methods and theories of multi-view representation learning based on the perspective of alignment, such as correlation-based alignment. Representative examples are canonical correlation analysis (CCA) and its several extensions. Then from the perspective of representation fusion we investigate the advancement of multi-view representation learning that ranges from generative methods including multi-modal topic learning, multi-view sparse coding, and multi-view latent space Markov networks, to neural network-based methods including multi-modal autoencoders, multi-view convolutional neural networks, and multi-modal recurrent neural networks. Further, we also investigate several important applications of multi-view representation learning. Overall, this survey aims to provide an insightful overview of theoretical foundation and state-of-the-art developments in the field of multi-view representation learning and to help researchers find the most appropriate tools for particular applications.

* Accepted by IEEE Transactions on Knowledge and Data Engineering 

  Access Paper or Ask Questions

"Factual" or "Emotional": Stylized Image Captioning with Adaptive Learning and Attention

Jul 29, 2018
Tianlang Chen, Zhongping Zhang, Quanzeng You, Chen Fang, Zhaowen Wang, Hailin Jin, Jiebo Luo

Generating stylized captions for an image is an emerging topic in image captioning. Given an image as input, it requires the system to generate a caption that has a specific style (e.g., humorous, romantic, positive, and negative) while describing the image content semantically accurately. In this paper, we propose a novel stylized image captioning model that effectively takes both requirements into consideration. To this end, we first devise a new variant of LSTM, named style-factual LSTM, as the building block of our model. It uses two groups of matrices to capture the factual and stylized knowledge, respectively, and automatically learns the word-level weights of the two groups based on previous context. In addition, when we train the model to capture stylized elements, we propose an adaptive learning approach based on a reference factual model, it provides factual knowledge to the model as the model learns from stylized caption labels, and can adaptively compute how much information to supply at each time step. We evaluate our model on two stylized image captioning datasets, which contain humorous/romantic captions and positive/negative captions, respectively. Experiments shows that our proposed model outperforms the state-of-the-art approaches, without using extra ground truth supervision.

* 17 pages, 7 figures, ECCV 2018 

  Access Paper or Ask Questions

Optimisation of photometric stereo methods by non-convex variational minimisation

Sep 29, 2017
Georg Radow, Laurent Hoeltgen, Yvain Quéau, Michael Breuß

Estimating shape and appearance of a three dimensional object from a given set of images is a classic research topic that is still actively pursued. Among the various techniques available, PS is distinguished by the assumption that the underlying input images are taken from the same point of view but under different lighting conditions. The most common techniques provide the shape information in terms of surface normals. In this work, we instead propose to minimise a much more natural objective function, namely the reprojection error in terms of depth. Minimising the resulting non-trivial variational model for PS allows to recover the depth of the photographed scene directly. As a solving strategy, we follow an approach based on a recently published optimisation scheme for non-convex and non-smooth cost functions. The main contributions of our paper are of theoretical nature. A technical novelty in our framework is the usage of matrix differential calculus. We supplement our approach by a detailed convergence analysis of the resulting optimisation algorithm and discuss possibilities to ease the computational complexity. At hand of an experimental evaluation we discuss important properties of the method. Overall, our strategy achieves more accurate results than competing approaches. The experiments also highlights some practical aspects of the underlying optimisation algorithm that may be of interest in a more general context.

* 18 pages, 18 Figures 

  Access Paper or Ask Questions

Agent-based computing from multi-agent systems to agent-based Models: a visual survey

Aug 19, 2017
Muaz A. Niazi, Amir Hussain

Agent-Based Computing is a diverse research domain concerned with the building of intelligent software based on the concept of "agents". In this paper, we use Scientometric analysis to analyze all sub-domains of agent-based computing. Our data consists of 1,064 journal articles indexed in the ISI web of knowledge published during a twenty year period: 1990-2010. These were retrieved using a topic search with various keywords commonly used in sub-domains of agent-based computing. In our proposed approach, we have employed a combination of two applications for analysis, namely Network Workbench and CiteSpace - wherein Network Workbench allowed for the analysis of complex network aspects of the domain, detailed visualization-based analysis of the bibliographic data was performed using CiteSpace. Our results include the identification of the largest cluster based on keywords, the timeline of publication of index terms, the core journals and key subject categories. We also identify the core authors, top countries of origin of the manuscripts along with core research institutes. Finally, our results have interestingly revealed the strong presence of agent-based computing in a number of non-computing related scientific domains including Life Sciences, Ecological Sciences and Social Sciences.

* Scientometrics 89.2 (2011): 479 
* 30 pages, 11 figures, 9 tables 

  Access Paper or Ask Questions

Face Deidentification with Generative Deep Neural Networks

Jul 28, 2017
Blaž Meden, Refik Can Mallı, Sebastjan Fabijan, Hazım Kemal Ekenel, Vitomir Štruc, Peter Peer

Face deidentification is an active topic amongst privacy and security researchers. Early deidentification methods relying on image blurring or pixelization were replaced in recent years with techniques based on formal anonymity models that provide privacy guaranties and at the same time aim at retaining certain characteristics of the data even after deidentification. The latter aspect is particularly important, as it allows to exploit the deidentified data in applications for which identity information is irrelevant. In this work we present a novel face deidentification pipeline, which ensures anonymity by synthesizing artificial surrogate faces using generative neural networks (GNNs). The generated faces are used to deidentify subjects in images or video, while preserving non-identity-related aspects of the data and consequently enabling data utilization. Since generative networks are very adaptive and can utilize a diverse set of parameters (pertaining to the appearance of the generated output in terms of facial expressions, gender, race, etc.), they represent a natural choice for the problem of face deidentification. To demonstrate the feasibility of our approach, we perform experiments using automated recognition tools and human annotators. Our results show that the recognition performance on deidentified images is close to chance, suggesting that the deidentification process based on GNNs is highly effective.

* IET Signal Processing Special Issue on Deidentification 2017 

  Access Paper or Ask Questions

Predicting and Understanding Law-Making with Word Vectors and an Ensemble Model

Apr 29, 2017
John J. Nay

Out of nearly 70,000 bills introduced in the U.S. Congress from 2001 to 2015, only 2,513 were enacted. We developed a machine learning approach to forecasting the probability that any bill will become law. Starting in 2001 with the 107th Congress, we trained models on data from previous Congresses, predicted all bills in the current Congress, and repeated until the 113th Congress served as the test. For prediction we scored each sentence of a bill with a language model that embeds legislative vocabulary into a high-dimensional, semantic-laden vector space. This language representation enables our investigation into which words increase the probability of enactment for any topic. To test the relative importance of text and context, we compared the text model to a context-only model that uses variables such as whether the bill's sponsor is in the majority party. To test the effect of changes to bills after their introduction on our ability to predict their final outcome, we compared using the bill text and meta-data available at the time of introduction with using the most recent data. At the time of introduction context-only predictions outperform text-only, and with the newest data text-only outperforms context-only. Combining text and context always performs best. We conducted a global sensitivity analysis on the combined model to determine important variables predicting enactment.

  Access Paper or Ask Questions