Paper Group AWR 154
Sequence Level Semantics Aggregation for Video Object Detection. Policy Search by Target Distribution Learning for Continuous Control. Quaternion Knowledge Graph Embeddings. Decompressing Knowledge Graph Representations for Link Prediction. Composition-based Multi-Relational Graph Convolutional Networks. InteractE: Improving Convolution-based Knowl …
Sequence Level Semantics Aggregation for Video Object Detection
| Title | Sequence Level Semantics Aggregation for Video Object Detection |
| Authors | Haiping Wu, Yuntao Chen, Naiyan Wang, Zhaoxiang Zhang |
| Abstract | Video objection detection (VID) has been a rising research direction in recent years. A central issue of VID is the appearance degradation of video frames caused by fast motion. This problem is essentially ill-posed for a single frame. Therefore, aggregating features from other frames becomes a natural choice. Existing methods rely heavily on optical flow or recurrent neural networks for feature aggregation. However, these methods emphasize more on the temporally nearby frames. In this work, we argue that aggregating features in the full-sequence level will lead to more discriminative and robust features for video object detection. To achieve this goal, we devise a novel Sequence Level Semantics Aggregation (SELSA) module. We further demonstrate the close relationship between the proposed method and the classic spectral clustering method, providing a novel view for understanding the VID problem. We test the proposed method on the ImageNet VID and the EPIC KITCHENS dataset and achieve new state-of-the-art results. Our method does not need complicated postprocessing methods such as Seq-NMS or Tubelet rescoring, which keeps the pipeline simple and clean. |
| Tasks | Object Detection, Video Object Detection, Video Recognition |
| Published | 2019-07-15 |
| URL | https://arxiv.org/abs/1907.06390v2 |
| https://arxiv.org/pdf/1907.06390v2.pdf | |
| PWC | https://paperswithcode.com/paper/sequence-level-semantics-aggregation-for |
| Repo | https://github.com/happywu/Sequence-Level-Semantics-Aggregation |
| Framework | mxnet |
Policy Search by Target Distribution Learning for Continuous Control
| Title | Policy Search by Target Distribution Learning for Continuous Control |
| Authors | Chuheng Zhang, Yuanqi Li, Jian Li |
| Abstract | We observe that several existing policy gradient methods (such as vanilla policy gradient, PPO, A2C) may suffer from overly large gradients when the current policy is close to deterministic (even in some very simple environments), leading to an unstable training process. To address this issue, we propose a new method, called \emph{target distribution learning} (TDL), for policy improvement in reinforcement learning. TDL alternates between proposing a target distribution and training the policy network to approach the target distribution. TDL is more effective in constraining the KL divergence between updated policies, and hence leads to more stable policy improvements over iterations. Our experiments show that TDL algorithms perform comparably to (or better than) state-of-the-art algorithms for most continuous control tasks in the MuJoCo environment while being more stable in training. |
| Tasks | Continuous Control, Policy Gradient Methods |
| Published | 2019-05-27 |
| URL | https://arxiv.org/abs/1905.11041v2 |
| https://arxiv.org/pdf/1905.11041v2.pdf | |
| PWC | https://paperswithcode.com/paper/policy-search-by-target-distribution-learning |
| Repo | https://github.com/targetdistributionlearning/target-distribution-learning |
| Framework | pytorch |
Quaternion Knowledge Graph Embeddings
| Title | Quaternion Knowledge Graph Embeddings |
| Authors | Shuai Zhang, Yi Tay, Lina Yao, Qi Liu |
| Abstract | In this work, we move beyond the traditional complex-valued representations, introducing more expressive hypercomplex representations to model entities and relations for knowledge graph embeddings. More specifically, quaternion embeddings, hypercomplex-valued embeddings with three imaginary components, are utilized to represent entities. Relations are modelled as rotations in the quaternion space. The advantages of the proposed approach are: (1) Latent inter-dependencies (between all components) are aptly captured with Hamilton product, encouraging a more compact interaction between entities and relations; (2) Quaternions enable expressive rotation in four-dimensional space and have more degree of freedom than rotation in complex plane; (3) The proposed framework is a generalization of ComplEx on hypercomplex space while offering better geometrical interpretations, concurrently satisfying the key desiderata of relational representation learning (i.e., modeling symmetry, anti-symmetry and inversion). Experimental results demonstrate that our method achieves state-of-the-art performance on four well-established knowledge graph completion benchmarks. |
| Tasks | Graph Embedding, Knowledge Graph Completion, Knowledge Graph Embedding, Knowledge Graph Embeddings, Knowledge Graphs, Link Prediction, Representation Learning |
| Published | 2019-04-23 |
| URL | https://arxiv.org/abs/1904.10281v3 |
| https://arxiv.org/pdf/1904.10281v3.pdf | |
| PWC | https://paperswithcode.com/paper/quaternion-knowledge-graph-embedding |
| Repo | https://github.com/cheungdaven/QuatE |
| Framework | pytorch |
Decompressing Knowledge Graph Representations for Link Prediction
| Title | Decompressing Knowledge Graph Representations for Link Prediction |
| Authors | Xiang Kong, Xianyang Chen, Eduard Hovy |
| Abstract | This paper studies the problem of predicting missing relationships between entities in knowledge graphs through learning their representations. Currently, the majority of existing link prediction models employ simple but intuitive scoring functions and relatively small embedding size so that they could be applied to large-scale knowledge graphs. However, these properties also restrict the ability to learn more expressive and robust features. Therefore, diverging from most of the prior works which focus on designing new objective functions, we propose, DeCom, a simple but effective mechanism to boost the performance of existing link predictors such as DistMult, ComplEx, etc, through extracting more expressive features while preventing overfitting by adding just a few extra parameters. Specifically, embeddings of entities and relationships are first decompressed to a more expressive and robust space by decompressing functions, then knowledge graph embedding models are trained in this new feature space. Experimental results on several benchmark knowledge graphs and advanced link prediction systems demonstrate the generalization and effectiveness of our method. Especially, RESCAL + DeCom achieves state-of-the-art performance on the FB15k-237 benchmark across all evaluation metrics. In addition, we also show that compared with DeCom, explicitly increasing the embedding size significantly increase the number of parameters but could not achieve promising performance improvement. |
| Tasks | Graph Embedding, Knowledge Graph Embedding, Knowledge Graphs, Link Prediction |
| Published | 2019-11-11 |
| URL | https://arxiv.org/abs/1911.04053v2 |
| https://arxiv.org/pdf/1911.04053v2.pdf | |
| PWC | https://paperswithcode.com/paper/decompressing-knowledge-graph-representations |
| Repo | https://github.com/shawnkx/Decom |
| Framework | pytorch |
Composition-based Multi-Relational Graph Convolutional Networks
| Title | Composition-based Multi-Relational Graph Convolutional Networks |
| Authors | Shikhar Vashishth, Soumya Sanyal, Vikram Nitin, Partha Talukdar |
| Abstract | Graph Convolutional Networks (GCNs) have recently been shown to be quite successful in modeling graph-structured data. However, the primary focus has been on handling simple undirected graphs. Multi-relational graphs are a more general and prevalent form of graphs where each edge has a label and direction associated with it. Most of the existing approaches to handle such graphs suffer from over-parameterization and are restricted to learning representations of nodes only. In this paper, we propose CompGCN, a novel Graph Convolutional framework which jointly embeds both nodes and relations in a relational graph. CompGCN leverages a variety of entity-relation composition operations from Knowledge Graph Embedding techniques and scales with the number of relations. It also generalizes several of the existing multi-relational GCN methods. We evaluate our proposed method on multiple tasks such as node classification, link prediction, and graph classification, and achieve demonstrably superior results. We make the source code of CompGCN available to foster reproducible research. |
| Tasks | Graph Classification, Graph Embedding, Knowledge Graph Embedding, Link Prediction, Node Classification |
| Published | 2019-11-08 |
| URL | https://arxiv.org/abs/1911.03082v2 |
| https://arxiv.org/pdf/1911.03082v2.pdf | |
| PWC | https://paperswithcode.com/paper/composition-based-multi-relational-graph |
| Repo | https://github.com/malllabiisc/CompGCN |
| Framework | pytorch |
InteractE: Improving Convolution-based Knowledge Graph Embeddings by Increasing Feature Interactions
| Title | InteractE: Improving Convolution-based Knowledge Graph Embeddings by Increasing Feature Interactions |
| Authors | Shikhar Vashishth, Soumya Sanyal, Vikram Nitin, Nilesh Agrawal, Partha Talukdar |
| Abstract | Most existing knowledge graphs suffer from incompleteness, which can be alleviated by inferring missing links based on known facts. One popular way to accomplish this is to generate low-dimensional embeddings of entities and relations, and use these to make inferences. ConvE, a recently proposed approach, applies convolutional filters on 2D reshapings of entity and relation embeddings in order to capture rich interactions between their components. However, the number of interactions that ConvE can capture is limited. In this paper, we analyze how increasing the number of these interactions affects link prediction performance, and utilize our observations to propose InteractE. InteractE is based on three key ideas – feature permutation, a novel feature reshaping, and circular convolution. Through extensive experiments, we find that InteractE outperforms state-of-the-art convolutional link prediction baselines on FB15k-237. Further, InteractE achieves an MRR score that is 9%, 7.5%, and 23% better than ConvE on the FB15k-237, WN18RR and YAGO3-10 datasets respectively. The results validate our central hypothesis – that increasing feature interaction is beneficial to link prediction performance. We make the source code of InteractE available to encourage reproducible research. |
| Tasks | Knowledge Graph Embeddings, Knowledge Graphs, Link Prediction |
| Published | 2019-11-01 |
| URL | https://arxiv.org/abs/1911.00219v2 |
| https://arxiv.org/pdf/1911.00219v2.pdf | |
| PWC | https://paperswithcode.com/paper/interacte-improving-convolution-based |
| Repo | https://github.com/malllabiisc/InteractE |
| Framework | pytorch |
Pay Less Attention with Lightweight and Dynamic Convolutions
| Title | Pay Less Attention with Lightweight and Dynamic Convolutions |
| Authors | Felix Wu, Angela Fan, Alexei Baevski, Yann N. Dauphin, Michael Auli |
| Abstract | Self-attention is a useful mechanism to build generative models for language and images. It determines the importance of context elements by comparing each element to the current time step. In this paper, we show that a very lightweight convolution can perform competitively to the best reported self-attention results. Next, we introduce dynamic convolutions which are simpler and more efficient than self-attention. We predict separate convolution kernels based solely on the current time-step in order to determine the importance of context elements. The number of operations required by this approach scales linearly in the input length, whereas self-attention is quadratic. Experiments on large-scale machine translation, language modeling and abstractive summarization show that dynamic convolutions improve over strong self-attention models. On the WMT’14 English-German test set dynamic convolutions achieve a new state of the art of 29.7 BLEU. |
| Tasks | Abstractive Text Summarization, Language Modelling, Machine Translation |
| Published | 2019-01-29 |
| URL | http://arxiv.org/abs/1901.10430v2 |
| http://arxiv.org/pdf/1901.10430v2.pdf | |
| PWC | https://paperswithcode.com/paper/pay-less-attention-with-lightweight-and |
| Repo | https://github.com/pytorch/fairseq |
| Framework | pytorch |
Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification
| Title | Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification |
| Authors | Daniel Borkan, Lucas Dixon, Jeffrey Sorensen, Nithum Thain, Lucy Vasserman |
| Abstract | Unintended bias in Machine Learning can manifest as systemic differences in performance for different demographic groups, potentially compounding existing challenges to fairness in society at large. In this paper, we introduce a suite of threshold-agnostic metrics that provide a nuanced view of this unintended bias, by considering the various ways that a classifier’s score distribution can vary across designated groups. We also introduce a large new test set of online comments with crowd-sourced annotations for identity references. We use this to show how our metrics can be used to find new and potentially subtle unintended bias in existing public models. |
| Tasks | Text Classification |
| Published | 2019-03-11 |
| URL | https://arxiv.org/abs/1903.04561v2 |
| https://arxiv.org/pdf/1903.04561v2.pdf | |
| PWC | https://paperswithcode.com/paper/nuanced-metrics-for-measuring-unintended-bias |
| Repo | https://github.com/JoshuaTHLiu/DataScience |
| Framework | none |
Effective Estimation of Deep Generative Language Models
| Title | Effective Estimation of Deep Generative Language Models |
| Authors | Tom Pelsmaeker, Wilker Aziz |
| Abstract | Advances in variational inference enable parameterisation of probabilistic models by deep neural networks. This combines the statistical transparency of the probabilistic modelling framework with the representational power of deep learning. Yet, it seems difficult to effectively estimate such models in the context of language modelling. Even models based on rather simple generative stories struggle to make use of additional structure due to a problem known as posterior collapse. We concentrate on one such model, namely, a variational auto-encoder, which we argue is an important building block in hierarchical probabilistic models of language. This paper contributes a sober view of the problem, a survey of techniques to address it, novel techniques, and extensions to the model. Our experiments on modelling written English text support a number of recommendations that should help researchers interested in this exciting field. |
| Tasks | Language Modelling |
| Published | 2019-04-17 |
| URL | https://arxiv.org/abs/1904.08194v2 |
| https://arxiv.org/pdf/1904.08194v2.pdf | |
| PWC | https://paperswithcode.com/paper/effective-estimation-of-deep-generative |
| Repo | https://github.com/tom-pelsmaeker/deep-generative-lm |
| Framework | pytorch |
Effective weakly supervised semantic frame induction using expression sharing in hierarchical hidden Markov models
| Title | Effective weakly supervised semantic frame induction using expression sharing in hierarchical hidden Markov models |
| Authors | Janneke van de Loo, Jort F. Gemmeke, Guy De Pauw, Bart Ons, Walter Daelemans, Hugo Van hamme |
| Abstract | We present a framework for the induction of semantic frames from utterances in the context of an adaptive command-and-control interface. The system is trained on an individual user’s utterances and the corresponding semantic frames representing controls. During training, no prior information on the alignment between utterance segments and frame slots and values is available. In addition, semantic frames in the training data can contain information that is not expressed in the utterances. To tackle this weakly supervised classification task, we propose a framework based on Hidden Markov Models (HMMs). Structural modifications, resulting in a hierarchical HMM, and an extension called expression sharing are introduced to minimize the amount of training time and effort required for the user. The dataset used for the present study is PATCOR, which contains commands uttered in the context of a vocally guided card game, Patience. Experiments were carried out on orthographic and phonetic transcriptions of commands, segmented on different levels of n-gram granularity. The experimental results show positive effects of all the studied system extensions, with some effect differences between the different input representations. Moreover, evaluation experiments on held-out data with the optimal system configuration show that the extended system is able to achieve high accuracies with relatively small amounts of training data. |
| Tasks | |
| Published | 2019-01-30 |
| URL | http://arxiv.org/abs/1901.10680v1 |
| http://arxiv.org/pdf/1901.10680v1.pdf | |
| PWC | https://paperswithcode.com/paper/effective-weakly-supervised-semantic-frame |
| Repo | https://github.com/clips/patcor |
| Framework | none |
ReshapeGAN: Object Reshaping by Providing A Single Reference Image
| Title | ReshapeGAN: Object Reshaping by Providing A Single Reference Image |
| Authors | Ziqiang Zheng, Yang Wu, Zhibin Yu, Yang Yang, Haiyong Zheng, Takeo Kanade |
| Abstract | The aim of this work is learning to reshape the object in an input image to an arbitrary new shape, by just simply providing a single reference image with an object instance in the desired shape. We propose a new Generative Adversarial Network (GAN) architecture for such an object reshaping problem, named ReshapeGAN. The network can be tailored for handling all kinds of problem settings, including both within-domain (or single-dataset) reshaping and cross-domain (typically across mutiple datasets) reshaping, with paired or unpaired training data. The appearance of the input object is preserved in all cases, and thus it is still identifiable after reshaping, which has never been achieved as far as we are aware. We present the tailored models of the proposed ReshapeGAN for all the problem settings, and have them tested on 8 kinds of reshaping tasks with 13 different datasets, demonstrating the ability of ReshapeGAN on generating convincing and superior results for object reshaping. To the best of our knowledge, we are the first to be able to make one GAN framework work on all such object reshaping tasks, especially the cross-domain tasks on handling multiple diverse datasets. We present here both ablation studies on our proposed ReshapeGAN models and comparisons with the state-of-the-art models when they are made comparable, using all kinds of applicable metrics that we are aware of. |
| Tasks | |
| Published | 2019-05-16 |
| URL | https://arxiv.org/abs/1905.06514v1 |
| https://arxiv.org/pdf/1905.06514v1.pdf | |
| PWC | https://paperswithcode.com/paper/reshapegan-object-reshaping-by-providing-a |
| Repo | https://github.com/zhengziqiang/ReshapeGAN |
| Framework | tf |
Uncertainty Aware Learning from Demonstrations in Multiple Contexts using Bayesian Neural Networks
| Title | Uncertainty Aware Learning from Demonstrations in Multiple Contexts using Bayesian Neural Networks |
| Authors | Sanjay Thakur, Herke van Hoof, Juan Camilo Gamboa Higuera, Doina Precup, David Meger |
| Abstract | Diversity of environments is a key challenge that causes learned robotic controllers to fail due to the discrepancies between the training and evaluation conditions. Training from demonstrations in various conditions can mitigate—but not completely prevent—such failures. Learned controllers such as neural networks typically do not have a notion of uncertainty that allows to diagnose an offset between training and testing conditions, and potentially intervene. In this work, we propose to use Bayesian Neural Networks, which have such a notion of uncertainty. We show that uncertainty can be leveraged to consistently detect situations in high-dimensional simulated and real robotic domains in which the performance of the learned controller would be sub-par. Also, we show that such an uncertainty based solution allows making an informed decision about when to invoke a fallback strategy. One fallback strategy is to request more data. We empirically show that providing data only when requested results in increased data-efficiency. |
| Tasks | |
| Published | 2019-03-13 |
| URL | http://arxiv.org/abs/1903.05697v1 |
| http://arxiv.org/pdf/1903.05697v1.pdf | |
| PWC | https://paperswithcode.com/paper/uncertainty-aware-learning-from |
| Repo | https://github.com/sanjaythakur/Uncertainty-aware-Imitation-Learning-on-Multiple-Tasks-using-Bayesian-Neural-Networks |
| Framework | tf |
Semi-supervised Sequence Modeling for Elastic Impedance Inversion
| Title | Semi-supervised Sequence Modeling for Elastic Impedance Inversion |
| Authors | Motaz Alfarraj, Ghassan AlRegib |
| Abstract | Recent applications of machine learning algorithms in the seismic domain have shown great potential in different areas such as seismic inversion and interpretation. However, such algorithms rarely enforce geophysical constraints - the lack of which might lead to undesirable results. To overcome this issue, we have developed a semi-supervised sequence modeling framework based on recurrent neural networks for elastic impedance inversion from multi-angle seismic data. Specifically, seismic traces and elastic impedance (EI) traces are modeled as a time series. Then, a neural-network-based inversion model comprising convolutional and recurrent neural layers is used to invert seismic data for EI. The proposed workflow uses well-log data to guide the inversion. In addition, it uses seismic forward modeling to regularize the training and to serve as a geophysical constraint for the inversion. The proposed workflow achieves an average correlation of 98% between the estimated and target EI using 10 well logs for training on a synthetic data set. |
| Tasks | Time Series |
| Published | 2019-08-19 |
| URL | https://arxiv.org/abs/1908.07849v1 |
| https://arxiv.org/pdf/1908.07849v1.pdf | |
| PWC | https://paperswithcode.com/paper/190807849 |
| Repo | https://github.com/motazalfarraj/Elastic-Impedance-Inversion-Using-Recurrent-Neural-Networks |
| Framework | pytorch |
signADAM: Learning Confidences for Deep Neural Networks
| Title | signADAM: Learning Confidences for Deep Neural Networks |
| Authors | Dong Wang, Yicheng Liu, Wenwo Tang, Fanhua Shang, Hongying Liu, Qigong Sun, Licheng Jiao |
| Abstract | In this paper, we propose a new first-order gradient-based algorithm to train deep neural networks. We first introduce the sign operation of stochastic gradients (as in sign-based methods, e.g., SIGN-SGD) into ADAM, which is called as signADAM. Moreover, in order to make the rate of fitting each feature closer, we define a confidence function to distinguish different components of gradients and apply it to our algorithm. It can generate more sparse gradients than existing algorithms do. We call this new algorithm signADAM++. In particular, both our algorithms are easy to implement and can speed up training of various deep neural networks. The motivation of signADAM++ is preferably learning features from the most different samples by updating large and useful gradients regardless of useless information in stochastic gradients. We also establish theoretical convergence guarantees for our algorithms. Empirical results on various datasets and models show that our algorithms yield much better performance than many state-of-the-art algorithms including SIGN-SGD, SIGNUM and ADAM. We also analyze the performance from multiple perspectives including the loss landscape and develop an adaptive method to further improve generalization. The source code is available at https://github.com/DongWanginxdu/signADAM-Learn-by-Confidence. |
| Tasks | |
| Published | 2019-07-21 |
| URL | https://arxiv.org/abs/1907.09008v1 |
| https://arxiv.org/pdf/1907.09008v1.pdf | |
| PWC | https://paperswithcode.com/paper/signadam-learning-confidences-for-deep-neural |
| Repo | https://github.com/DongWanginxdu/signADAM-Learn-by-Confidence |
| Framework | pytorch |
A Closer Look at Few-shot Classification
| Title | A Closer Look at Few-shot Classification |
| Authors | Wei-Yu Chen, Yen-Cheng Liu, Zsolt Kira, Yu-Chiang Frank Wang, Jia-Bin Huang |
| Abstract | Few-shot classification aims to learn a classifier to recognize unseen classes during training with limited labeled examples. While significant progress has been made, the growing complexity of network designs, meta-learning algorithms, and differences in implementation details make a fair comparison difficult. In this paper, we present 1) a consistent comparative analysis of several representative few-shot classification algorithms, with results showing that deeper backbones significantly reduce the performance differences among methods on datasets with limited domain differences, 2) a modified baseline method that surprisingly achieves competitive performance when compared with the state-of-the-art on both the \miniI and the CUB datasets, and 3) a new experimental setting for evaluating the cross-domain generalization ability for few-shot classification algorithms. Our results reveal that reducing intra-class variation is an important factor when the feature backbone is shallow, but not as critical when using deeper backbones. In a realistic cross-domain evaluation setting, we show that a baseline method with a standard fine-tuning practice compares favorably against other state-of-the-art few-shot learning algorithms. |
| Tasks | Domain Generalization, Few-Shot Image Classification, Few-Shot Learning, Meta-Learning |
| Published | 2019-04-08 |
| URL | https://arxiv.org/abs/1904.04232v2 |
| https://arxiv.org/pdf/1904.04232v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-closer-look-at-few-shot-classification-1 |
| Repo | https://github.com/wyharveychen/CloserLookFewShot |
| Framework | pytorch |
