October 20, 2019

2880 words 14 mins read

Paper Group AWR 211

Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks. Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds. Personalizing Dialogue Agents: I have a dog, do you have pets too?. On the Evaluation of Semantic Phenomena in Neural Machine Translation Using Natural Language Inference. Whiteni …

Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks


Title	Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks
Authors	Ali Shafahi, W. Ronny Huang, Mahyar Najibi, Octavian Suciu, Christoph Studer, Tudor Dumitras, Tom Goldstein
Abstract	Data poisoning is an attack on machine learning models wherein the attacker adds examples to the training set to manipulate the behavior of the model at test time. This paper explores poisoning attacks on neural nets. The proposed attacks use “clean-labels”; they don’t require the attacker to have any control over the labeling of training data. They are also targeted; they control the behavior of the classifier on a $\textit{specific}$ test instance without degrading overall classifier performance. For example, an attacker could add a seemingly innocuous image (that is properly labeled) to a training set for a face recognition engine, and control the identity of a chosen person at test time. Because the attacker does not need to control the labeling function, poisons could be entered into the training set simply by leaving them on the web and waiting for them to be scraped by a data collection bot. We present an optimization-based method for crafting poisons, and show that just one single poison image can control classifier behavior when transfer learning is used. For full end-to-end training, we present a “watermarking” strategy that makes poisoning reliable using multiple ($\approx$50) poisoned training instances. We demonstrate our method by generating poisoned frog images from the CIFAR dataset and using them to manipulate image classifiers.
Tasks	data poisoning, Face Recognition, Transfer Learning
Published	2018-04-03
URL	http://arxiv.org/abs/1804.00792v2
PDF	http://arxiv.org/pdf/1804.00792v2.pdf
PWC	https://paperswithcode.com/paper/poison-frogs-targeted-clean-label-poisoning
Repo	https://github.com/ashafahi/inceptionv3-transferLearn-poison
Framework	tf

Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds


Title	Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds
Authors	Nathaniel Thomas, Tess Smidt, Steven Kearnes, Lusann Yang, Li Li, Kai Kohlhoff, Patrick Riley
Abstract	We introduce tensor field neural networks, which are locally equivariant to 3D rotations, translations, and permutations of points at every layer. 3D rotation equivariance removes the need for data augmentation to identify features in arbitrary orientations. Our network uses filters built from spherical harmonics; due to the mathematical consequences of this filter choice, each layer accepts as input (and guarantees as output) scalars, vectors, and higher-order tensors, in the geometric sense of these terms. We demonstrate the capabilities of tensor field networks with tasks in geometry, physics, and chemistry.
Tasks	Data Augmentation
Published	2018-02-22
URL	http://arxiv.org/abs/1802.08219v3
PDF	http://arxiv.org/pdf/1802.08219v3.pdf
PWC	https://paperswithcode.com/paper/tensor-field-networks-rotation-and
Repo	https://github.com/mariogeiger/se3cnn
Framework	pytorch

Personalizing Dialogue Agents: I have a dog, do you have pets too?


Title	Personalizing Dialogue Agents: I have a dog, do you have pets too?
Authors	Saizheng Zhang, Emily Dinan, Jack Urbanek, Arthur Szlam, Douwe Kiela, Jason Weston
Abstract	Chit-chat models are known to have several problems: they lack specificity, do not display a consistent personality and are often not very captivating. In this work we present the task of making chit-chat more engaging by conditioning on profile information. We collect data and train models to (i) condition on their given profile information; and (ii) information about the person they are talking to, resulting in improved dialogues, as measured by next utterance prediction. Since (ii) is initially unknown our model is trained to engage its partner with personal topics, and we show the resulting dialogue can be used to predict profile information about the interlocutors.
Tasks
Published	2018-01-22
URL	http://arxiv.org/abs/1801.07243v5
PDF	http://arxiv.org/pdf/1801.07243v5.pdf
PWC	https://paperswithcode.com/paper/personalizing-dialogue-agents-i-have-a-dog-do
Repo	https://github.com/facebookresearch/ParlAI
Framework	pytorch

On the Evaluation of Semantic Phenomena in Neural Machine Translation Using Natural Language Inference


Title	On the Evaluation of Semantic Phenomena in Neural Machine Translation Using Natural Language Inference
Authors	Adam Poliak, Yonatan Belinkov, James Glass, Benjamin Van Durme
Abstract	We propose a process for investigating the extent to which sentence representations arising from neural machine translation (NMT) systems encode distinct semantic phenomena. We use these representations as features to train a natural language inference (NLI) classifier based on datasets recast from existing semantic annotations. In applying this process to a representative NMT system, we find its encoder appears most suited to supporting inferences at the syntax-semantics interface, as compared to anaphora resolution requiring world-knowledge. We conclude with a discussion on the merits and potential deficiencies of the existing process, and how it may be improved and extended as a broader framework for evaluating semantic coverage.
Tasks	Machine Translation, Natural Language Inference
Published	2018-04-25
URL	http://arxiv.org/abs/1804.09779v2
PDF	http://arxiv.org/pdf/1804.09779v2.pdf
PWC	https://paperswithcode.com/paper/on-the-evaluation-of-semantic-phenomena-in
Repo	https://github.com/boknilev/nmt-repr-analysis
Framework	pytorch

Whitening and Coloring batch transform for GANs


Title	Whitening and Coloring batch transform for GANs
Authors	Aliaksandr Siarohin, Enver Sangineto, Nicu Sebe
Abstract	Batch Normalization (BN) is a common technique used to speed-up and stabilize training. On the other hand, the learnable parameters of BN are commonly used in conditional Generative Adversarial Networks (cGANs) for representing class-specific information using conditional Batch Normalization (cBN). In this paper we propose to generalize both BN and cBN using a Whitening and Coloring based batch normalization. We show that our conditional Coloring can represent categorical conditioning information which largely helps the cGAN qualitative results. Moreover, we show that full-feature whitening is important in a general GAN scenario in which the training process is known to be highly unstable. We test our approach on different datasets and using different GAN networks and training protocols, showing a consistent improvement in all the tested frameworks. Our CIFAR-10 conditioned results are higher than all previous works on this dataset.
Tasks	Image Generation
Published	2018-06-01
URL	http://arxiv.org/abs/1806.00420v2
PDF	http://arxiv.org/pdf/1806.00420v2.pdf
PWC	https://paperswithcode.com/paper/whitening-and-coloring-batch-transform-for
Repo	https://github.com/AliaksandrSiarohin/wc-gan
Framework	tf

SlideRunner - A Tool for Massive Cell Annotations in Whole Slide Images


Title	SlideRunner - A Tool for Massive Cell Annotations in Whole Slide Images
Authors	Marc Aubreville, Christof Bertram, Robert Klopfleisch, Andreas Maier
Abstract	Large-scale image data such as digital whole-slide histology images pose a challenging task at annotation software solutions. Today, a number of good solutions with varying scopes exist. For cell annotation, however, we find that many do not match the prerequisites for fast annotations. Especially in the field of mitosis detection, it is assumed that detection accuracy could significantly benefit from larger annotation databases that are currently however very troublesome to produce. Further, multiple independent (blind) expert labels are a big asset for such databases, yet there is currently no tool for this kind of annotation available. To ease this tedious process of expert annotation and grading, we introduce SlideRunner, an open source annotation and visualization tool for digital histopathology, developed in close cooperation with two pathologists. SlideRunner is capable of setting annotations like object centers (for e.g. cells) as well as object boundaries (e.g. for tumor outlines). It provides single-click annotations as well as a blind mode for multi-annotations, where the expert is directly shown the microscopy image containing the cells that he has not yet rated.
Tasks	Mitosis Detection
Published	2018-02-07
URL	http://arxiv.org/abs/1802.02347v1
PDF	http://arxiv.org/pdf/1802.02347v1.pdf
PWC	https://paperswithcode.com/paper/sliderunner-a-tool-for-massive-cell
Repo	https://github.com/maubreville/SlideRunner
Framework	tf

Domain Agnostic Real-Valued Specificity Prediction


Title	Domain Agnostic Real-Valued Specificity Prediction
Authors	Wei-Jen Ko, Greg Durrett, Junyi Jessy Li
Abstract	Sentence specificity quantifies the level of detail in a sentence, characterizing the organization of information in discourse. While this information is useful for many downstream applications, specificity prediction systems predict very coarse labels (binary or ternary) and are trained on and tailored toward specific domains (e.g., news). The goal of this work is to generalize specificity prediction to domains where no labeled data is available and output more nuanced real-valued specificity ratings. We present an unsupervised domain adaptation system for sentence specificity prediction, specifically designed to output real-valued estimates from binary training labels. To calibrate the values of these predictions appropriately, we regularize the posterior distribution of the labels towards a reference distribution. We show that our framework generalizes well to three different domains with 50%~68% mean absolute error reduction than the current state-of-the-art system trained for news sentence specificity. We also demonstrate the potential of our work in improving the quality and informativeness of dialogue generation systems.
Tasks	Dialogue Generation, Domain Adaptation, Unsupervised Domain Adaptation
Published	2018-11-13
URL	http://arxiv.org/abs/1811.05085v2
PDF	http://arxiv.org/pdf/1811.05085v2.pdf
PWC	https://paperswithcode.com/paper/domain-agnostic-real-valued-specificity
Repo	https://github.com/wjko2/Domain-Agnostic-Sentence-Specificity-Prediction
Framework	pytorch


Title	A Multi-Modal Chinese Poetry Generation Model
Authors	Dayiheng Liu, Quan Guo, Wubo Li, Jiancheng Lv
Abstract	Recent studies in sequence-to-sequence learning demonstrate that RNN encoder-decoder structure can successfully generate Chinese poetry. However, existing methods can only generate poetry with a given first line or user’s intent theme. In this paper, we proposed a three-stage multi-modal Chinese poetry generation approach. Given a picture, the first line, the title and the other lines of the poem are successively generated in three stages. According to the characteristics of Chinese poems, we propose a hierarchy-attention seq2seq model which can effectively capture character, phrase, and sentence information between contexts and improve the symmetry delivered in poems. In addition, the Latent Dirichlet allocation (LDA) model is utilized for title generation and improve the relevance of the whole poem and the title. Compared with strong baseline, the experimental results demonstrate the effectiveness of our approach, using machine evaluations as well as human judgments.
Tasks
Published	2018-06-26
URL	http://arxiv.org/abs/1806.09792v1
PDF	http://arxiv.org/pdf/1806.09792v1.pdf
PWC	https://paperswithcode.com/paper/a-multi-modal-chinese-poetry-generation-model
Repo	https://github.com/Epoch-Mengying/Generating-Poetry-with-Chatbot
Framework	none

LAG: Lazily Aggregated Gradient for Communication-Efficient Distributed Learning


Title	LAG: Lazily Aggregated Gradient for Communication-Efficient Distributed Learning
Authors	Tianyi Chen, Georgios B. Giannakis, Tao Sun, Wotao Yin
Abstract	This paper presents a new class of gradient methods for distributed machine learning that adaptively skip the gradient calculations to learn with reduced communication and computation. Simple rules are designed to detect slowly-varying gradients and, therefore, trigger the reuse of outdated gradients. The resultant gradient-based algorithms are termed Lazily Aggregated Gradient — justifying our acronym LAG used henceforth. Theoretically, the merits of this contribution are: i) the convergence rate is the same as batch gradient descent in strongly-convex, convex, and nonconvex smooth cases; and, ii) if the distributed datasets are heterogeneous (quantified by certain measurable constants), the communication rounds needed to achieve a targeted accuracy are reduced thanks to the adaptive reuse of lagged gradients. Numerical experiments on both synthetic and real data corroborate a significant communication reduction compared to alternatives.
Tasks
Published	2018-05-25
URL	http://arxiv.org/abs/1805.09965v2
PDF	http://arxiv.org/pdf/1805.09965v2.pdf
PWC	https://paperswithcode.com/paper/lag-lazily-aggregated-gradient-for
Repo	https://github.com/chentianyi1991/LAG-code
Framework	none

FineGAN: Unsupervised Hierarchical Disentanglement for Fine-Grained Object Generation and Discovery


Title	FineGAN: Unsupervised Hierarchical Disentanglement for Fine-Grained Object Generation and Discovery
Authors	Krishna Kumar Singh, Utkarsh Ojha, Yong Jae Lee
Abstract	We propose FineGAN, a novel unsupervised GAN framework, which disentangles the background, object shape, and object appearance to hierarchically generate images of fine-grained object categories. To disentangle the factors without supervision, our key idea is to use information theory to associate each factor to a latent code, and to condition the relationships between the codes in a specific way to induce the desired hierarchy. Through extensive experiments, we show that FineGAN achieves the desired disentanglement to generate realistic and diverse images belonging to fine-grained classes of birds, dogs, and cars. Using FineGAN’s automatically learned features, we also cluster real images as a first attempt at solving the novel problem of unsupervised fine-grained object category discovery. Our code/models/demo can be found at https://github.com/kkanshul/finegan
Tasks	Conditional Image Generation, Fine-Grained Visual Categorization, Image Clustering
Published	2018-11-27
URL	http://arxiv.org/abs/1811.11155v2
PDF	http://arxiv.org/pdf/1811.11155v2.pdf
PWC	https://paperswithcode.com/paper/finegan-unsupervised-hierarchical
Repo	https://github.com/kkanshul/finegan
Framework	pytorch

Stay With Me: Lifetime Maximization Through Heteroscedastic Linear Bandits With Reneging


Title	Stay With Me: Lifetime Maximization Through Heteroscedastic Linear Bandits With Reneging
Authors	Ping-Chun Hsieh, Xi Liu, Anirban Bhattacharya, P. R. Kumar
Abstract	Sequential decision making for lifetime maximization is a critical problem in many real-world applications, such as medical treatment and portfolio selection. In these applications, a “reneging” phenomenon, where participants may disengage from future interactions after observing an unsatisfiable outcome, is rather prevalent. To address the above issue, this paper proposes a model of heteroscedastic linear bandits with reneging, which allows each participant to have a distinct “satisfaction level,” with any interaction outcome falling short of that level resulting in that participant reneging. Moreover, it allows the variance of the outcome to be context-dependent. Based on this model, we develop a UCB-type policy, namely HR-UCB, and prove that it achieves $\mathcal{O}\big(\sqrt{{T}(\log({T}))^{3}}\big)$ regret. Finally, we validate the performance of HR-UCB via simulations.
Tasks	Decision Making, Multi-Armed Bandits
Published	2018-10-29
URL	https://arxiv.org/abs/1810.12418v4
PDF	https://arxiv.org/pdf/1810.12418v4.pdf
PWC	https://paperswithcode.com/paper/heteroscedastic-bandits-with-reneging
Repo	https://github.com/Xi-Liu/heteroscedasticbandits
Framework	none

Mapping Images to Scene Graphs with Permutation-Invariant Structured Prediction


Title	Mapping Images to Scene Graphs with Permutation-Invariant Structured Prediction
Authors	Roei Herzig, Moshiko Raboh, Gal Chechik, Jonathan Berant, Amir Globerson
Abstract	Machine understanding of complex images is a key goal of artificial intelligence. One challenge underlying this task is that visual scenes contain multiple inter-related objects, and that global context plays an important role in interpreting the scene. A natural modeling framework for capturing such effects is structured prediction, which optimizes over complex labels, while modeling within-label interactions. However, it is unclear what principles should guide the design of a structured prediction model that utilizes the power of deep learning components. Here we propose a design principle for such architectures that follows from a natural requirement of permutation invariance. We prove a necessary and sufficient characterization for architectures that follow this invariance, and discuss its implication on model design. Finally, we show that the resulting model achieves new state of the art results on the Visual Genome scene graph labeling benchmark, outperforming all recent approaches.
Tasks	Structured Prediction
Published	2018-02-15
URL	http://arxiv.org/abs/1802.05451v4
PDF	http://arxiv.org/pdf/1802.05451v4.pdf
PWC	https://paperswithcode.com/paper/mapping-images-to-scene-graphs-with
Repo	https://github.com/shikorab/SceneGraph
Framework	tf

Hyperbolic Neural Networks


Title	Hyperbolic Neural Networks
Authors	Octavian-Eugen Ganea, Gary Bécigneul, Thomas Hofmann
Abstract	Hyperbolic spaces have recently gained momentum in the context of machine learning due to their high capacity and tree-likeliness properties. However, the representational power of hyperbolic geometry is not yet on par with Euclidean geometry, mostly because of the absence of corresponding hyperbolic neural network layers. This makes it hard to use hyperbolic embeddings in downstream tasks. Here, we bridge this gap in a principled manner by combining the formalism of M"obius gyrovector spaces with the Riemannian geometry of the Poincar'e model of hyperbolic spaces. As a result, we derive hyperbolic versions of important deep learning tools: multinomial logistic regression, feed-forward and recurrent neural networks such as gated recurrent units. This allows to embed sequential data and perform classification in the hyperbolic space. Empirically, we show that, even if hyperbolic optimization tools are limited, hyperbolic sentence embeddings either outperform or are on par with their Euclidean variants on textual entailment and noisy-prefix recognition tasks.
Tasks	Graph Representation Learning, Natural Language Inference, Sentence Embeddings
Published	2018-05-23
URL	http://arxiv.org/abs/1805.09112v2
PDF	http://arxiv.org/pdf/1805.09112v2.pdf
PWC	https://paperswithcode.com/paper/hyperbolic-neural-networks
Repo	https://github.com/dalab/hyperbolic_nn
Framework	tf

Guided Feature Transformation (GFT): A Neural Language Grounding Module for Embodied Agents


Title	Guided Feature Transformation (GFT): A Neural Language Grounding Module for Embodied Agents
Authors	Haonan Yu, Xiaochen Lian, Haichao Zhang, Wei Xu
Abstract	Recently there has been a rising interest in training agents, embodied in virtual environments, to perform language-directed tasks by deep reinforcement learning. In this paper, we propose a simple but effective neural language grounding module for embodied agents that can be trained end to end from scratch taking raw pixels, unstructured linguistic commands, and sparse rewards as the inputs. We model the language grounding process as a language-guided transformation of visual features, where latent sentence embeddings are used as the transformation matrices. In several language-directed navigation tasks that feature challenging partial observability and require simple reasoning, our module significantly outperforms the state of the art. We also release XWorld3D, an easy-to-customize 3D environment that can potentially be modified to evaluate a variety of embodied agents.
Tasks	Sentence Embeddings
Published	2018-05-22
URL	http://arxiv.org/abs/1805.08329v2
PDF	http://arxiv.org/pdf/1805.08329v2.pdf
PWC	https://paperswithcode.com/paper/guided-feature-transformation-gft-a-neural
Repo	https://github.com/PaddlePaddle/XWorld
Framework	none

Deep Density-based Image Clustering


Title	Deep Density-based Image Clustering
Authors	Yazhou Ren, Ni Wang, Mingxia Li, Zenglin Xu
Abstract	Recently, deep clustering, which is able to perform feature learning that favors clustering tasks via deep neural networks, has achieved remarkable performance in image clustering applications. However, the existing deep clustering algorithms generally need the number of clusters in advance, which is usually unknown in real-world tasks. In addition, the initial cluster centers in the learned feature space are generated by $k$-means. This only works well on spherical clusters and probably leads to unstable clustering results. In this paper, we propose a two-stage deep density-based image clustering (DDC) framework to address these issues. The first stage is to train a deep convolutional autoencoder (CAE) to extract low-dimensional feature representations from high-dimensional image data, and then apply t-SNE to further reduce the data to a 2-dimensional space favoring density-based clustering algorithms. The second stage is to apply the developed density-based clustering technique on the 2-dimensional embedded data to automatically recognize an appropriate number of clusters with arbitrary shapes. Concretely, a number of local clusters are generated to capture the local structures of clusters, and then are merged via their density relationship to form the final clustering result. Experiments demonstrate that the proposed DDC achieves comparable or even better clustering performance than state-of-the-art deep clustering methods, even though the number of clusters is not given.
Tasks	Image Clustering
Published	2018-12-11
URL	http://arxiv.org/abs/1812.04287v1
PDF	http://arxiv.org/pdf/1812.04287v1.pdf
PWC	https://paperswithcode.com/paper/deep-density-based-image-clustering
Repo	https://github.com/waynezhanghk/gacluster
Framework	pytorch