Paper Group ANR 112
A Survey on Bias and Fairness in Machine Learning. Distribution Density, Tails, and Outliers in Machine Learning: Metrics and Applications. Polytopes, lattices, and spherical codes for the nearest neighbor problem. Using an AI creativity system to explore how aesthetic experiences are processed along the brains perceptual neural pathways. Multi-sub …
A Survey on Bias and Fairness in Machine Learning
| Title | A Survey on Bias and Fairness in Machine Learning |
| Authors | Ninareh Mehrabi, Fred Morstatter, Nripsuta Saxena, Kristina Lerman, Aram Galstyan |
| Abstract | With the widespread use of AI systems and applications in our everyday lives, it is important to take fairness issues into consideration while designing and engineering these types of systems. Such systems can be used in many sensitive environments to make important and life-changing decisions; thus, it is crucial to ensure that the decisions do not reflect discriminatory behavior toward certain groups or populations. We have recently seen work in machine learning, natural language processing, and deep learning that addresses such challenges in different subdomains. With the commercialization of these systems, researchers are becoming aware of the biases that these applications can contain and have attempted to address them. In this survey we investigated different real-world applications that have shown biases in various ways, and we listed different sources of biases that can affect AI applications. We then created a taxonomy for fairness definitions that machine learning researchers have defined in order to avoid the existing bias in AI systems. In addition to that, we examined different domains and subdomains in AI showing what researchers have observed with regard to unfair outcomes in the state-of-the-art methods and how they have tried to address them. There are still many future directions and solutions that can be taken to mitigate the problem of bias in AI systems. We are hoping that this survey will motivate researchers to tackle these issues in the near future by observing existing work in their respective fields. |
| Tasks | |
| Published | 2019-08-23 |
| URL | https://arxiv.org/abs/1908.09635v2 |
| https://arxiv.org/pdf/1908.09635v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-survey-on-bias-and-fairness-in-machine |
| Repo | |
| Framework | |
Distribution Density, Tails, and Outliers in Machine Learning: Metrics and Applications
| Title | Distribution Density, Tails, and Outliers in Machine Learning: Metrics and Applications |
| Authors | Nicholas Carlini, Úlfar Erlingsson, Nicolas Papernot |
| Abstract | We develop techniques to quantify the degree to which a given (training or testing) example is an outlier in the underlying distribution. We evaluate five methods to score examples in a dataset by how well-represented the examples are, for different plausible definitions of “well-represented”, and apply these to four common datasets: MNIST, Fashion-MNIST, CIFAR-10, and ImageNet. Despite being independent approaches, we find all five are highly correlated, suggesting that the notion of being well-represented can be quantified. Among other uses, we find these methods can be combined to identify (a) prototypical examples (that match human expectations); (b) memorized training examples; and, (c) uncommon submodes of the dataset. Further, we show how we can utilize our metrics to determine an improved ordering for curriculum learning, and impact adversarial robustness. We release all metric values on training and test sets we studied. |
| Tasks | |
| Published | 2019-10-29 |
| URL | https://arxiv.org/abs/1910.13427v1 |
| https://arxiv.org/pdf/1910.13427v1.pdf | |
| PWC | https://paperswithcode.com/paper/191013427 |
| Repo | |
| Framework | |
Polytopes, lattices, and spherical codes for the nearest neighbor problem
| Title | Polytopes, lattices, and spherical codes for the nearest neighbor problem |
| Authors | Thijs Laarhoven |
| Abstract | We study locality-sensitive hash methods for the nearest neighbor problem for the angular distance, focusing on the approach of first projecting down onto a low-dimensional subspace, and then partitioning the projected vectors according to Voronoi cells induced by a suitable spherical code. This approach generalizes and interpolates between the fast but suboptimal hyperplane hashing of Charikar [STOC’02] and the asymptotically optimal but practically often slower hash families of Andoni-Indyk [FOCS’06], Andoni-Indyk-Nguyen-Razenshteyn [SODA’14] and Andoni-Indyk-Laarhoven-Razenshteyn-Schmidt [NIPS’15]. We set up a framework for analyzing the performance of any spherical code in this context, and we provide results for various codes from the literature, such as those related to regular polytopes and root lattices. Similar to hyperplane hashing, and unlike cross-polytope hashing, our analysis of collision probabilities and query exponents is exact and does not hide order terms which vanish only for large $d$, facilitating an easy parameter selection. For the two-dimensional case, we derive closed-form expressions for arbitrary spherical codes, and we show that the equilateral triangle is optimal, achieving a better performance than the two-dimensional analogues of hyperplane and cross-polytope hashing. In three and four dimensions, we numerically find that the tetrahedron, $5$-cell, and $16$-cell achieve the best query exponents, while in five or more dimensions orthoplices appear to outperform regular simplices, as well as the root lattice families $A_k$ and $D_k$. We argue that in higher dimensions, larger spherical codes will likely exist which will outperform orthoplices in theory, and we argue why using the $D_k$ root lattices will likely lead to better results in practice, due to a better trade-off between the asymptotic query exponent and the concrete costs of hashing. |
| Tasks | |
| Published | 2019-07-10 |
| URL | https://arxiv.org/abs/1907.04628v1 |
| https://arxiv.org/pdf/1907.04628v1.pdf | |
| PWC | https://paperswithcode.com/paper/polytopes-lattices-and-spherical-codes-for |
| Repo | |
| Framework | |
Using an AI creativity system to explore how aesthetic experiences are processed along the brains perceptual neural pathways
| Title | Using an AI creativity system to explore how aesthetic experiences are processed along the brains perceptual neural pathways |
| Authors | Vanessa Utz, Steve DiPaola |
| Abstract | With the increased sophistication of AI techniques, the application of these systems has been expanding to ever newer fields. Increasingly, these systems are being used in modeling of human aesthetics and creativity, e.g. how humans create artworks and design products. Our lab has developed one such AI creativity deep learning system that can be used to create artworks in the form of images and videos. In this paper, we describe this system and its use in studying the human visual system and the formation of aesthetic experiences. Specifically, we show how time-based AI created media can be used to explore the nature of the dual-pathway neuro-architecture of the human visual system and how this relates to higher cognitive judgments such as aesthetic experiences that rely on these divergent information streams. We propose a theoretical framework for how the movement within percepts such as video clips, causes the engagement of reflexive attention and a subsequent focus on visual information that are primarily processed via the dorsal stream, thereby modulating aesthetic experiences that rely on information relayed via the ventral stream. We outline our recent study in support of our proposed framework, which serves as the first study that investigates the relationship between the two visual streams and aesthetic experiences. |
| Tasks | |
| Published | 2019-09-15 |
| URL | https://arxiv.org/abs/1909.06904v1 |
| https://arxiv.org/pdf/1909.06904v1.pdf | |
| PWC | https://paperswithcode.com/paper/using-an-ai-creativity-system-to-explore-how |
| Repo | |
| Framework | |
Multi-subject MEG/EEG source imaging with sparse multi-task regression
| Title | Multi-subject MEG/EEG source imaging with sparse multi-task regression |
| Authors | Hicham Janati, Thomas Bazeille, Bertrand Thirion, Marco Cuturi, Alexandre Gramfort |
| Abstract | Magnetoencephalography and electroencephalography (M/EEG) are non-invasive modalities that measure the weak electromagnetic fields generated by neural activity. Estimating the location and magnitude of the current sources that generated these electromagnetic fields is a challenging ill-posed regression problem known as \emph{source imaging}. When considering a group study, a common approach consists in carrying out the regression tasks independently for each subject. An alternative is to jointly localize sources for all subjects taken together, while enforcing some similarity between them. By pooling all measurements in a single multi-task regression, one makes the problem better posed, offering the ability to identify more sources and with greater precision. The Minimum Wasserstein Estimates (MWE) promotes focal activations that do not perfectly overlap for all subjects, thanks to a regularizer based on Optimal Transport (OT) metrics. MWE promotes spatial proximity on the cortical mantel while coping with the varying noise levels across subjects. On realistic simulations, MWE decreases the localization error by up to 4 mm per source compared to individual solutions. Experiments on the Cam-CAN dataset show a considerable improvement in spatial specificity in population imaging. Our analysis of a multimodal dataset shows how multi-subject source localization closes the gap between MEG and fMRI for brain mapping. |
| Tasks | EEG |
| Published | 2019-10-03 |
| URL | https://arxiv.org/abs/1910.01914v2 |
| https://arxiv.org/pdf/1910.01914v2.pdf | |
| PWC | https://paperswithcode.com/paper/multi-subject-megeeg-source-imaging-with |
| Repo | |
| Framework | |
A Symmetric Encoder-Decoder with Residual Block for Infrared and Visible Image Fusion
| Title | A Symmetric Encoder-Decoder with Residual Block for Infrared and Visible Image Fusion |
| Authors | Lihua Jian, Xiaomin Yang, Zheng Liu, Gwanggil Jeon, Mingliang Gao, David Chisholm |
| Abstract | In computer vision and image processing tasks, image fusion has evolved into an attractive research field. However, recent existing image fusion methods are mostly built on pixel-level operations, which may produce unacceptable artifacts and are time-consuming. In this paper, a symmetric encoder-decoder with a residual block (SEDR) for infrared and visible image fusion is proposed. For the training stage, the SEDR network is trained with a new dataset to obtain a fixed feature extractor. For the fusion stage, first, the trained model is utilized to extract the intermediate features and compensation features of two source images. Then, extracted intermediate features are used to generate two attention maps, which are multiplied to the input features for refinement. In addition, the compensation features generated by the first two convolutional layers are merged and passed to the corresponding deconvolutional layers. At last, the refined features are fused for decoding to reconstruct the final fused image. Experimental results demonstrate that the proposed fusion method (named as SEDRFuse) outperforms the state-of-the-art fusion methods in terms of both subjective and objective evaluations. |
| Tasks | Infrared And Visible Image Fusion |
| Published | 2019-05-27 |
| URL | https://arxiv.org/abs/1905.11447v1 |
| https://arxiv.org/pdf/1905.11447v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-symmetric-encoder-decoder-with-residual |
| Repo | |
| Framework | |
A Novel Graphical Lasso based approach towards Segmentation Analysis in Energy Game-Theoretic Frameworks
| Title | A Novel Graphical Lasso based approach towards Segmentation Analysis in Energy Game-Theoretic Frameworks |
| Authors | Hari Prasanna Das, Ioannis C. Konstantakopoulos, Aummul Baneen Manasawala, Tanya Veeravalli, Huihan Liu, Costas J. Spanos |
| Abstract | Energy game-theoretic frameworks have emerged to be a successful strategy to encourage energy efficient behavior in large scale by leveraging human-in-the-loop strategy. A number of such frameworks have been introduced over the years which formulate the energy saving process as a competitive game with appropriate incentives for energy efficient players. However, prior works involve an incentive design mechanism which is dependent on knowledge of utility functions for all the players in the game, which is hard to compute especially when the number of players is high, common in energy game-theoretic frameworks. Our research proposes that the utilities of players in such a framework can be grouped together to a relatively small number of clusters, and the clusters can then be targeted with tailored incentives. The key to above segmentation analysis is to learn the features leading to human decision making towards energy usage in competitive environments. We propose a novel graphical lasso based approach to perform such segmentation, by studying the feature correlations in a real-world energy social game dataset. To further improve the explainability of the model, we perform causality study using grangers causality. Proposed segmentation analysis results in characteristic clusters demonstrating different energy usage behaviors. We also present avenues to implement intelligent incentive design using proposed segmentation method. |
| Tasks | Decision Making |
| Published | 2019-10-05 |
| URL | https://arxiv.org/abs/1910.02217v1 |
| https://arxiv.org/pdf/1910.02217v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-novel-graphical-lasso-based-approach |
| Repo | |
| Framework | |
An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition
| Title | An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition |
| Authors | Chenyang Si, Wentao Chen, Wei Wang, Liang Wang, Tieniu Tan |
| Abstract | Skeleton-based action recognition is an important task that requires the adequate understanding of movement characteristics of a human action from the given skeleton sequence. Recent studies have shown that exploring spatial and temporal features of the skeleton sequence is vital for this task. Nevertheless, how to effectively extract discriminative spatial and temporal features is still a challenging problem. In this paper, we propose a novel Attention Enhanced Graph Convolutional LSTM Network (AGC-LSTM) for human action recognition from skeleton data. The proposed AGC-LSTM can not only capture discriminative features in spatial configuration and temporal dynamics but also explore the co-occurrence relationship between spatial and temporal domains. We also present a temporal hierarchical architecture to increases temporal receptive fields of the top AGC-LSTM layer, which boosts the ability to learn the high-level semantic representation and significantly reduces the computation cost. Furthermore, to select discriminative spatial information, the attention mechanism is employed to enhance information of key joints in each AGC-LSTM layer. Experimental results on two datasets are provided: NTU RGB+D dataset and Northwestern-UCLA dataset. The comparison results demonstrate the effectiveness of our approach and show that our approach outperforms the state-of-the-art methods on both datasets. |
| Tasks | Skeleton Based Action Recognition, Temporal Action Localization |
| Published | 2019-02-25 |
| URL | http://arxiv.org/abs/1902.09130v2 |
| http://arxiv.org/pdf/1902.09130v2.pdf | |
| PWC | https://paperswithcode.com/paper/an-attention-enhanced-graph-convolutional |
| Repo | |
| Framework | |
Weighted Lifted Codes: Local Correctabilities and Application to Robust Private Information Retrieval
| Title | Weighted Lifted Codes: Local Correctabilities and Application to Robust Private Information Retrieval |
| Authors | Julien Lavauzelle, Jade Nardi |
| Abstract | Low degree Reed-Muller codes are known to satisfy local decoding properties which find applications in private information retrieval (PIR) protocols, for instance. However, their practical instantiation encounters a first barrier due to their poor information rate in the low degree regime. This lead the community to design codes with similar local properties but larger dimension, namely the lifted Reed-Solomon codes. However, a second practical barrier appears when one requires that the PIR protocol resists collusions of servers. In this paper, we propose a solution to this problem by considering \emph{weighted} Reed-Muller codes. We prove that such codes allow us to build PIR protocols with optimal computation complexity and resisting to a small number of colluding servers. In order to improve the dimension of the codes, we then introduce an analogue of the lifting process for weigthed degrees. With a careful analysis of their degree sets, we notably show that the weighted lifting of Reed-Solomon codes produces families of codes with remarkable asymptotic parameters. |
| Tasks | Information Retrieval |
| Published | 2019-04-18 |
| URL | http://arxiv.org/abs/1904.08696v1 |
| http://arxiv.org/pdf/1904.08696v1.pdf | |
| PWC | https://paperswithcode.com/paper/weighted-lifted-codes-local-correctabilities |
| Repo | |
| Framework | |
Apple Leaf Disease Identification through Region-of-Interest-Aware Deep Convolutional Neural Network
| Title | Apple Leaf Disease Identification through Region-of-Interest-Aware Deep Convolutional Neural Network |
| Authors | Hee-Jin Yu, Chang-Hwan Son |
| Abstract | A new method of recognizing apple leaf diseases through region-of-interest-aware deep convolutional neural network is proposed in this paper. The primary idea is that leaf disease symptoms appear in the leaf area whereas the background region contains no useful information regarding leaf diseases. To realize this idea, two subnetworks are first designed. One is for the division of the input image into three areas: background, leaf area, and spot area indicating the leaf diseases, which is the region of interest, and the other is for the classification of leaf diseases. The two subnetworks exhibit the architecture types of an encoder-decoder network and VGG network, respectively; subsequently, they are trained separately through transfer learning with a new training set containing class information, according to the types of leaf diseases and the ground truth images where the background, leaf area, and spot area are separated. Next, to connect these subnetworks and subsequently train the connected whole network in an end-to-end manner, the predicted ROI feature map is stacked on the top of the input image through a fusion layer, and subsequently fed into the subnetwork used for the leaf disease identification. The experimental results indicate that correct recognition accuracy can be increased using the predicted ROI feature map. It is also shown that the proposed method obtains better performance than the conventional state-of-the-art methods: transfer-learning-based methods, bilinear model, and multiscale-based deep feature extraction, and pooling approach. |
| Tasks | Transfer Learning |
| Published | 2019-03-25 |
| URL | https://arxiv.org/abs/1903.10356v2 |
| https://arxiv.org/pdf/1903.10356v2.pdf | |
| PWC | https://paperswithcode.com/paper/apple-leaf-disease-identification-through |
| Repo | |
| Framework | |
Exploring Kernel Functions in the Softmax Layer for Contextual Word Classification
| Title | Exploring Kernel Functions in the Softmax Layer for Contextual Word Classification |
| Authors | Yingbo Gao, Christian Herold, Weiyue Wang, Hermann Ney |
| Abstract | Prominently used in support vector machines and logistic regressions, kernel functions (kernels) can implicitly map data points into high dimensional spaces and make it easier to learn complex decision boundaries. In this work, by replacing the inner product function in the softmax layer, we explore the use of kernels for contextual word classification. In order to compare the individual kernels, experiments are conducted on standard language modeling and machine translation tasks. We observe a wide range of performances across different kernel settings. Extending the results, we look at the gradient properties, investigate various mixture strategies and examine the disambiguation abilities. |
| Tasks | Language Modelling, Machine Translation |
| Published | 2019-10-28 |
| URL | https://arxiv.org/abs/1910.12554v1 |
| https://arxiv.org/pdf/1910.12554v1.pdf | |
| PWC | https://paperswithcode.com/paper/exploring-kernel-functions-in-the-softmax |
| Repo | |
| Framework | |
Rethinking the Number of Channels for the Convolutional Neural Network
| Title | Rethinking the Number of Channels for the Convolutional Neural Network |
| Authors | Hui Zhu, Zhulin An, Chuanguang Yang, Xiaolong Hu, Kaiqiang Xu, Yongjun Xu |
| Abstract | Latest algorithms for automatic neural architecture search perform remarkable but few of them can effectively design the number of channels for convolutional neural networks and consume less computational efforts. In this paper, we propose a method for efficient automatic architecture search which is special to the widths of networks instead of the connections of neural architecture. Our method, functionally incremental search based on function-preserving, will explore the number of channels rapidly while controlling the number of parameters of the target network. On CIFAR-10 and CIFAR-100 classification, our method using minimal computational resources (0.4~1.3 GPU-days) can discover more efficient rules of the widths of networks to improve the accuracy by about 0.5% on CIFAR-10 and a~2.33% on CIFAR-100 with fewer number of parameters. In particular, our method is suitable for exploring the number of channels of almost any convolutional neural network rapidly. |
| Tasks | Neural Architecture Search |
| Published | 2019-09-04 |
| URL | https://arxiv.org/abs/1909.01861v1 |
| https://arxiv.org/pdf/1909.01861v1.pdf | |
| PWC | https://paperswithcode.com/paper/rethinking-the-number-of-channels-for-the |
| Repo | |
| Framework | |
A Communication-Efficient Algorithm for Exponentially Fast Non-Bayesian Learning in Networks
| Title | A Communication-Efficient Algorithm for Exponentially Fast Non-Bayesian Learning in Networks |
| Authors | Aritra Mitra, John A. Richards, Shreyas Sundaram |
| Abstract | We introduce a simple time-triggered protocol to achieve communication-efficient non-Bayesian learning over a network. Specifically, we consider a scenario where a group of agents interact over a graph with the aim of discerning the true state of the world that generates their joint observation profiles. To address this problem, we propose a novel distributed learning rule wherein agents aggregate neighboring beliefs based on a min-protocol, and the inter-communication intervals grow geometrically at a rate $a \geq 1$. Despite such sparse communication, we show that each agent is still able to rule out every false hypothesis exponentially fast with probability $1$, as long as $a$ is finite. For the special case when communication occurs at every time-step, i.e., when $a=1$, we prove that the asymptotic learning rates resulting from our algorithm are network-structure independent, and a strict improvement upon those existing in the literature. In contrast, when $a>1$, our analysis reveals that the asymptotic learning rates vary across agents, and exhibit a non-trivial dependence on the network topology coupled with the relative entropies of the agents’ likelihood models. This motivates us to consider the problem of allocating signal structures to agents to maximize appropriate performance metrics. In certain special cases, we show that the eccentricity centrality and the decay centrality of the underlying graph help identify optimal allocations; for more general scenarios, we bound the deviation from the optimal allocation as a function of the parameter $a$, and the diameter of the communication graph. |
| Tasks | |
| Published | 2019-09-04 |
| URL | https://arxiv.org/abs/1909.01505v1 |
| https://arxiv.org/pdf/1909.01505v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-communication-efficient-algorithm-for |
| Repo | |
| Framework | |
Projection-free nonconvex stochastic optimization on Riemannian manifolds
| Title | Projection-free nonconvex stochastic optimization on Riemannian manifolds |
| Authors | Melanie Weber, Suvrit Sra |
| Abstract | We study stochastic projection-free methods for constrained optimization of smooth functions on Riemannian manifolds, i.e., with additional constraints beyond the parameter domain being a manifold. Specifically, we introduce stochastic Riemannian Frank-Wolfe methods for nonconvex and geodesically convex problems. We present algorithms for both purely stochastic optimization and finite-sum problems. For the latter, we develop variance-reduced methods, including a Riemannian adaptation of the recently proposed Spider technique. For all settings, we recover convergence rates that are comparable to the best-known rates for their Euclidean counterparts. Finally, we discuss applications to two classic tasks: The computation of the Karcher mean of positive definite matrices and Wasserstein barycenters for multivariate normal distributions. For both tasks, stochastic Fw methods yield state-of-the-art empirical performance. |
| Tasks | Stochastic Optimization |
| Published | 2019-10-09 |
| URL | https://arxiv.org/abs/1910.04194v2 |
| https://arxiv.org/pdf/1910.04194v2.pdf | |
| PWC | https://paperswithcode.com/paper/nonconvex-stochastic-optimization-on |
| Repo | |
| Framework | |
Person Re-identification in Videos by Analyzing Spatio-Temporal Tubes
| Title | Person Re-identification in Videos by Analyzing Spatio-Temporal Tubes |
| Authors | Sk. Arif Ahmed, Debi Prosad Dogra, Heeseung Choi, Seungho Chae, Ig-Jae Kim |
| Abstract | Typical person re-identification frameworks search for k best matches in a gallery of images that are often collected in varying conditions. The gallery may contain image sequences when re-identification is done on videos. However, such a process is time consuming as re-identification has to be carried out multiple times. In this paper, we extract spatio-temporal sequences of frames (referred to as tubes) of moving persons and apply a multi-stage processing to match a given query tube with a gallery of stored tubes recorded through other cameras. Initially, we apply a binary classifier to remove noisy images from the input query tube. In the next step, we use a key-pose detection-based query minimization. This reduces the length of the query tube by removing redundant frames. Finally, a 3-stage hierarchical re-identification framework is used to rank the output tubes as per the matching scores. Experiments with publicly available video re-identification datasets reveal that our framework is better than state-of-the-art methods. It ranks the tubes with an increased CMC accuracy of 6-8% across multiple datasets. Also, our method significantly reduces the number of false positives. A new video re-identification dataset, named Tube-based Reidentification Video Dataset (TRiViD), has been prepared with an aim to help the re-identification research community |
| Tasks | Person Re-Identification |
| Published | 2019-02-13 |
| URL | http://arxiv.org/abs/1902.04856v1 |
| http://arxiv.org/pdf/1902.04856v1.pdf | |
| PWC | https://paperswithcode.com/paper/person-re-identification-in-videos-by |
| Repo | |
| Framework | |
