Paper Group AWR 119
Predicting Organic Reaction Outcomes with Weisfeiler-Lehman Network. Cross Temporal Recurrent Networks for Ranking Question Answer Pairs. The Statistical Recurrent Unit. MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks. Vision-Based Assessment of Parkinsonism and Levodopa-Induced Dyskinesia with Deep Learning Pose Es …
Predicting Organic Reaction Outcomes with Weisfeiler-Lehman Network
| Title | Predicting Organic Reaction Outcomes with Weisfeiler-Lehman Network |
| Authors | Wengong Jin, Connor W. Coley, Regina Barzilay, Tommi Jaakkola |
| Abstract | The prediction of organic reaction outcomes is a fundamental problem in computational chemistry. Since a reaction may involve hundreds of atoms, fully exploring the space of possible transformations is intractable. The current solution utilizes reaction templates to limit the space, but it suffers from coverage and efficiency issues. In this paper, we propose a template-free approach to efficiently explore the space of product molecules by first pinpointing the reaction center – the set of nodes and edges where graph edits occur. Since only a small number of atoms contribute to reaction center, we can directly enumerate candidate products. The generated candidates are scored by a Weisfeiler-Lehman Difference Network that models high-order interactions between changes occurring at nodes across the molecule. Our framework outperforms the top-performing template-based approach with a 10% margin, while running orders of magnitude faster. Finally, we demonstrate that the model accuracy rivals the performance of domain experts. |
| Tasks | |
| Published | 2017-09-13 |
| URL | http://arxiv.org/abs/1709.04555v3 |
| http://arxiv.org/pdf/1709.04555v3.pdf | |
| PWC | https://paperswithcode.com/paper/predicting-organic-reaction-outcomes-with |
| Repo | https://github.com/wengong-jin/nips17-rexgen |
| Framework | tf |
Cross Temporal Recurrent Networks for Ranking Question Answer Pairs
| Title | Cross Temporal Recurrent Networks for Ranking Question Answer Pairs |
| Authors | Yi Tay, Luu Anh Tuan, Siu Cheung Hui |
| Abstract | Temporal gates play a significant role in modern recurrent-based neural encoders, enabling fine-grained control over recursive compositional operations over time. In recurrent models such as the long short-term memory (LSTM), temporal gates control the amount of information retained or discarded over time, not only playing an important role in influencing the learned representations but also serving as a protection against vanishing gradients. This paper explores the idea of learning temporal gates for sequence pairs (question and answer), jointly influencing the learned representations in a pairwise manner. In our approach, temporal gates are learned via 1D convolutional layers and then subsequently cross applied across question and answer for joint learning. Empirically, we show that this conceptually simple sharing of temporal gates can lead to competitive performance across multiple benchmarks. Intuitively, what our network achieves can be interpreted as learning representations of question and answer pairs that are aware of what each other is remembering or forgetting, i.e., pairwise temporal gating. Via extensive experiments, we show that our proposed model achieves state-of-the-art performance on two community-based QA datasets and competitive performance on one factoid-based QA dataset. |
| Tasks | |
| Published | 2017-11-21 |
| URL | http://arxiv.org/abs/1711.07656v1 |
| http://arxiv.org/pdf/1711.07656v1.pdf | |
| PWC | https://paperswithcode.com/paper/cross-temporal-recurrent-networks-for-ranking |
| Repo | https://github.com/vanzytay/YahooQA_Splits |
| Framework | none |
The Statistical Recurrent Unit
| Title | The Statistical Recurrent Unit |
| Authors | Junier B. Oliva, Barnabas Poczos, Jeff Schneider |
| Abstract | Sophisticated gated recurrent neural network architectures like LSTMs and GRUs have been shown to be highly effective in a myriad of applications. We develop an un-gated unit, the statistical recurrent unit (SRU), that is able to learn long term dependencies in data by only keeping moving averages of statistics. The SRU’s architecture is simple, un-gated, and contains a comparable number of parameters to LSTMs; yet, SRUs perform favorably to more sophisticated LSTM and GRU alternatives, often outperforming one or both in various tasks. We show the efficacy of SRUs as compared to LSTMs and GRUs in an unbiased manner by optimizing respective architectures’ hyperparameters in a Bayesian optimization scheme for both synthetic and real-world tasks. |
| Tasks | |
| Published | 2017-03-01 |
| URL | http://arxiv.org/abs/1703.00381v1 |
| http://arxiv.org/pdf/1703.00381v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-statistical-recurrent-unit |
| Repo | https://github.com/mirandawork/sru |
| Framework | none |
MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks
| Title | MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks |
| Authors | Ariel Gordon, Elad Eban, Ofir Nachum, Bo Chen, Hao Wu, Tien-Ju Yang, Edward Choi |
| Abstract | We present MorphNet, an approach to automate the design of neural network structures. MorphNet iteratively shrinks and expands a network, shrinking via a resource-weighted sparsifying regularizer on activations and expanding via a uniform multiplicative factor on all layers. In contrast to previous approaches, our method is scalable to large networks, adaptable to specific resource constraints (e.g. the number of floating-point operations per inference), and capable of increasing the network’s performance. When applied to standard network architectures on a wide variety of datasets, our approach discovers novel structures in each domain, obtaining higher performance while respecting the resource constraint. |
| Tasks | Neural Architecture Search |
| Published | 2017-11-18 |
| URL | http://arxiv.org/abs/1711.06798v3 |
| http://arxiv.org/pdf/1711.06798v3.pdf | |
| PWC | https://paperswithcode.com/paper/morphnet-fast-simple-resource-constrained |
| Repo | https://github.com/tensorflow/models/tree/master/research/morph_net |
| Framework | tf |
Vision-Based Assessment of Parkinsonism and Levodopa-Induced Dyskinesia with Deep Learning Pose Estimation
| Title | Vision-Based Assessment of Parkinsonism and Levodopa-Induced Dyskinesia with Deep Learning Pose Estimation |
| Authors | Michael H. Li, Tiago A. Mestre, Susan H. Fox, Babak Taati |
| Abstract | Objective: To apply deep learning pose estimation algorithms for vision-based assessment of parkinsonism and levodopa-induced dyskinesia (LID). Methods: Nine participants with Parkinson’s disease (PD) and LID completed a levodopa infusion protocol, where symptoms were assessed at regular intervals using the Unified Dyskinesia Rating Scale (UDysRS) and Unified Parkinson’s Disease Rating Scale (UPDRS). A state-of-the-art deep learning pose estimation method was used to extract movement trajectories from videos of PD assessments. Features of the movement trajectories were used to detect and estimate the severity of parkinsonism and LID using random forest. Communication and drinking tasks were used to assess LID, while leg agility and toe tapping tasks were used to assess parkinsonism. Feature sets from tasks were also combined to predict total UDysRS and UPDRS Part III scores. Results: For LID, the communication task yielded the best results for dyskinesia (severity estimation: r = 0.661, detection: AUC = 0.930). For parkinsonism, leg agility had better results for severity estimation (r = 0.618), while toe tapping was better for detection (AUC = 0.773). UDysRS and UPDRS Part III scores were predicted with r = 0.741 and 0.530, respectively. Conclusion: This paper presents the first application of deep learning for vision-based assessment of parkinsonism and LID and demonstrates promising performance for the future translation of deep learning to PD clinical practices. Significance: The proposed system provides insight into the potential of computer vision and deep learning for clinical application in PD. |
| Tasks | Pose Estimation |
| Published | 2017-07-25 |
| URL | http://arxiv.org/abs/1707.09416v2 |
| http://arxiv.org/pdf/1707.09416v2.pdf | |
| PWC | https://paperswithcode.com/paper/vision-based-assessment-of-parkinsonism-and |
| Repo | https://github.com/limi44/Parkinson-s-Pose-Estimation-Dataset |
| Framework | none |
Differentiable lower bound for expected BLEU score
| Title | Differentiable lower bound for expected BLEU score |
| Authors | Vlad Zhukov, Eugene Golikov, Maksim Kretov |
| Abstract | In natural language processing tasks performance of the models is often measured with some non-differentiable metric, such as BLEU score. To use efficient gradient-based methods for optimization, it is a common workaround to optimize some surrogate loss function. This approach is effective if optimization of such loss also results in improving target metric. The corresponding problem is referred to as loss-evaluation mismatch. In the present work we propose a method for calculation of differentiable lower bound of expected BLEU score that does not involve computationally expensive sampling procedure such as the one required when using REINFORCE rule from reinforcement learning (RL) framework. |
| Tasks | |
| Published | 2017-12-13 |
| URL | http://arxiv.org/abs/1712.04708v4 |
| http://arxiv.org/pdf/1712.04708v4.pdf | |
| PWC | https://paperswithcode.com/paper/differentiable-lower-bound-for-expected-bleu |
| Repo | https://github.com/deepmipt/expected_bleu |
| Framework | pytorch |
SkiMap: An Efficient Mapping Framework for Robot Navigation
| Title | SkiMap: An Efficient Mapping Framework for Robot Navigation |
| Authors | Daniele De Gregorio, Luigi Di Stefano |
| Abstract | We present a novel mapping framework for robot navigation which features a multi-level querying system capable to obtain rapidly representations as diverse as a 3D voxel grid, a 2.5D height map and a 2D occupancy grid. These are inherently embedded into a memory and time efficient core data structure organized as a Tree of SkipLists. Compared to the well-known Octree representation, our approach exhibits a better time efficiency, thanks to its simple and highly parallelizable computational structure, and a similar memory footprint when mapping large workspaces. Peculiarly within the realm of mapping for robot navigation, our framework supports realtime erosion and re-integration of measurements upon reception of optimized poses from the sensor tracker, so as to improve continuously the accuracy of the map. |
| Tasks | Robot Navigation |
| Published | 2017-04-19 |
| URL | http://arxiv.org/abs/1704.05832v1 |
| http://arxiv.org/pdf/1704.05832v1.pdf | |
| PWC | https://paperswithcode.com/paper/skimap-an-efficient-mapping-framework-for |
| Repo | https://github.com/m4nh/skimap_ros |
| Framework | tf |
Learning 3D Human Pose from Structure and Motion
| Title | Learning 3D Human Pose from Structure and Motion |
| Authors | Rishabh Dabral, Anurag Mundhada, Uday Kusupati, Safeer Afaque, Abhishek Sharma, Arjun Jain |
| Abstract | 3D human pose estimation from a single image is a challenging problem, especially for in-the-wild settings due to the lack of 3D annotated data. We propose two anatomically inspired loss functions and use them with a weakly-supervised learning framework to jointly learn from large-scale in-the-wild 2D and indoor/synthetic 3D data. We also present a simple temporal network that exploits temporal and structural cues present in predicted pose sequences to temporally harmonize the pose estimations. We carefully analyze the proposed contributions through loss surface visualizations and sensitivity analysis to facilitate deeper understanding of their working mechanism. Our complete pipeline improves the state-of-the-art by 11.8% and 12% on Human3.6M and MPI-INF-3DHP, respectively, and runs at 30 FPS on a commodity graphics card. |
| Tasks | 3D Human Pose Estimation, Pose Estimation |
| Published | 2017-11-25 |
| URL | http://arxiv.org/abs/1711.09250v2 |
| http://arxiv.org/pdf/1711.09250v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-3d-human-pose-from-structure-and |
| Repo | https://github.com/anuragmundhada/3dpose-demo-iitb |
| Framework | torch |
Self-supervised Deep Reinforcement Learning with Generalized Computation Graphs for Robot Navigation
| Title | Self-supervised Deep Reinforcement Learning with Generalized Computation Graphs for Robot Navigation |
| Authors | Gregory Kahn, Adam Villaflor, Bosen Ding, Pieter Abbeel, Sergey Levine |
| Abstract | Enabling robots to autonomously navigate complex environments is essential for real-world deployment. Prior methods approach this problem by having the robot maintain an internal map of the world, and then use a localization and planning method to navigate through the internal map. However, these approaches often include a variety of assumptions, are computationally intensive, and do not learn from failures. In contrast, learning-based methods improve as the robot acts in the environment, but are difficult to deploy in the real-world due to their high sample complexity. To address the need to learn complex policies with few samples, we propose a generalized computation graph that subsumes value-based model-free methods and model-based methods, with specific instantiations interpolating between model-free and model-based. We then instantiate this graph to form a navigation model that learns from raw images and is sample efficient. Our simulated car experiments explore the design decisions of our navigation model, and show our approach outperforms single-step and $N$-step double Q-learning. We also evaluate our approach on a real-world RC car and show it can learn to navigate through a complex indoor environment with a few hours of fully autonomous, self-supervised training. Videos of the experiments and code can be found at github.com/gkahn13/gcg |
| Tasks | Q-Learning, Robot Navigation |
| Published | 2017-09-29 |
| URL | http://arxiv.org/abs/1709.10489v3 |
| http://arxiv.org/pdf/1709.10489v3.pdf | |
| PWC | https://paperswithcode.com/paper/self-supervised-deep-reinforcement-learning |
| Repo | https://github.com/abefetterman/hamstir-gym |
| Framework | tf |
Bilateral Multi-Perspective Matching for Natural Language Sentences
| Title | Bilateral Multi-Perspective Matching for Natural Language Sentences |
| Authors | Zhiguo Wang, Wael Hamza, Radu Florian |
| Abstract | Natural language sentence matching is a fundamental technology for a variety of tasks. Previous approaches either match sentences from a single direction or only apply single granular (word-by-word or sentence-by-sentence) matching. In this work, we propose a bilateral multi-perspective matching (BiMPM) model under the “matching-aggregation” framework. Given two sentences $P$ and $Q$, our model first encodes them with a BiLSTM encoder. Next, we match the two encoded sentences in two directions $P \rightarrow Q$ and $P \leftarrow Q$. In each matching direction, each time step of one sentence is matched against all time-steps of the other sentence from multiple perspectives. Then, another BiLSTM layer is utilized to aggregate the matching results into a fix-length matching vector. Finally, based on the matching vector, the decision is made through a fully connected layer. We evaluate our model on three tasks: paraphrase identification, natural language inference and answer sentence selection. Experimental results on standard benchmark datasets show that our model achieves the state-of-the-art performance on all tasks. |
| Tasks | Natural Language Inference, Paraphrase Identification |
| Published | 2017-02-13 |
| URL | http://arxiv.org/abs/1702.03814v3 |
| http://arxiv.org/pdf/1702.03814v3.pdf | |
| PWC | https://paperswithcode.com/paper/bilateral-multi-perspective-matching-for |
| Repo | https://github.com/Elvirasun28/quora-question-duplicate |
| Framework | tf |
Sketched Answer Set Programming
| Title | Sketched Answer Set Programming |
| Authors | Sergey Paramonov, Christian Bessiere, Anton Dries, Luc De Raedt |
| Abstract | Answer Set Programming (ASP) is a powerful modeling formalism for combinatorial problems. However, writing ASP models is not trivial. We propose a novel method, called Sketched Answer Set Programming (SkASP), aiming at supporting the user in resolving this issue. The user writes an ASP program while marking uncertain parts open with question marks. In addition, the user provides a number of positive and negative examples of the desired program behaviour. The sketched model is rewritten into another ASP program, which is solved by traditional methods. As a result, the user obtains a functional and reusable ASP program modelling her problem. We evaluate our approach on 21 well known puzzles and combinatorial problems inspired by Karp’s 21 NP-complete problems and demonstrate a use-case for a database application based on ASP. |
| Tasks | |
| Published | 2017-05-21 |
| URL | http://arxiv.org/abs/1705.07429v2 |
| http://arxiv.org/pdf/1705.07429v2.pdf | |
| PWC | https://paperswithcode.com/paper/sketched-answer-set-programming |
| Repo | https://github.com/SergeyParamonov/sketching |
| Framework | none |
Fuzzy Approach Topic Discovery in Health and Medical Corpora
| Title | Fuzzy Approach Topic Discovery in Health and Medical Corpora |
| Authors | Amir Karami, Aryya Gangopadhyay, Bin Zhou, Hadi Kharrazi |
| Abstract | The majority of medical documents and electronic health records (EHRs) are in text format that poses a challenge for data processing and finding relevant documents. Looking for ways to automatically retrieve the enormous amount of health and medical knowledge has always been an intriguing topic. Powerful methods have been developed in recent years to make the text processing automatic. One of the popular approaches to retrieve information based on discovering the themes in health & medical corpora is topic modeling, however, this approach still needs new perspectives. In this research we describe fuzzy latent semantic analysis (FLSA), a novel approach in topic modeling using fuzzy perspective. FLSA can handle health & medical corpora redundancy issue and provides a new method to estimate the number of topics. The quantitative evaluations show that FLSA produces superior performance and features to latent Dirichlet allocation (LDA), the most popular topic model. |
| Tasks | |
| Published | 2017-05-02 |
| URL | http://arxiv.org/abs/1705.00995v2 |
| http://arxiv.org/pdf/1705.00995v2.pdf | |
| PWC | https://paperswithcode.com/paper/fuzzy-approach-topic-discovery-in-health-and |
| Repo | https://github.com/amir-karami/Health-News-Tweets-Data |
| Framework | none |
AutoEncoder by Forest
| Title | AutoEncoder by Forest |
| Authors | Ji Feng, Zhi-Hua Zhou |
| Abstract | Auto-encoding is an important task which is typically realized by deep neural networks (DNNs) such as convolutional neural networks (CNN). In this paper, we propose EncoderForest (abbrv. eForest), the first tree ensemble based auto-encoder. We present a procedure for enabling forests to do backward reconstruction by utilizing the equivalent classes defined by decision paths of the trees, and demonstrate its usage in both supervised and unsupervised setting. Experiments show that, compared with DNN autoencoders, eForest is able to obtain lower reconstruction error with fast training speed, while the model itself is reusable and damage-tolerable. |
| Tasks | |
| Published | 2017-09-26 |
| URL | http://arxiv.org/abs/1709.09018v1 |
| http://arxiv.org/pdf/1709.09018v1.pdf | |
| PWC | https://paperswithcode.com/paper/autoencoder-by-forest |
| Repo | https://github.com/kingfengji/eForest |
| Framework | none |
SeGAN: Segmenting and Generating the Invisible
| Title | SeGAN: Segmenting and Generating the Invisible |
| Authors | Kiana Ehsani, Roozbeh Mottaghi, Ali Farhadi |
| Abstract | Objects often occlude each other in scenes; Inferring their appearance beyond their visible parts plays an important role in scene understanding, depth estimation, object interaction and manipulation. In this paper, we study the challenging problem of completing the appearance of occluded objects. Doing so requires knowing which pixels to paint (segmenting the invisible parts of objects) and what color to paint them (generating the invisible parts). Our proposed novel solution, SeGAN, jointly optimizes for both segmentation and generation of the invisible parts of objects. Our experimental results show that: (a) SeGAN can learn to generate the appearance of the occluded parts of objects; (b) SeGAN outperforms state-of-the-art segmentation baselines for the invisible parts of objects; (c) trained on synthetic photo realistic images, SeGAN can reliably segment natural images; (d) by reasoning about occluder occludee relations, our method can infer depth layering. |
| Tasks | Depth Estimation, Scene Understanding |
| Published | 2017-03-29 |
| URL | http://arxiv.org/abs/1703.10239v3 |
| http://arxiv.org/pdf/1703.10239v3.pdf | |
| PWC | https://paperswithcode.com/paper/segan-segmenting-and-generating-the-invisible |
| Repo | https://github.com/ehsanik/SeGAN |
| Framework | torch |
Dual Discriminator Generative Adversarial Nets
| Title | Dual Discriminator Generative Adversarial Nets |
| Authors | Tu Dinh Nguyen, Trung Le, Hung Vu, Dinh Phung |
| Abstract | We propose in this paper a novel approach to tackle the problem of mode collapse encountered in generative adversarial network (GAN). Our idea is intuitive but proven to be very effective, especially in addressing some key limitations of GAN. In essence, it combines the Kullback-Leibler (KL) and reverse KL divergences into a unified objective function, thus it exploits the complementary statistical properties from these divergences to effectively diversify the estimated density in capturing multi-modes. We term our method dual discriminator generative adversarial nets (D2GAN) which, unlike GAN, has two discriminators; and together with a generator, it also has the analogy of a minimax game, wherein a discriminator rewards high scores for samples from data distribution whilst another discriminator, conversely, favoring data from the generator, and the generator produces data to fool both two discriminators. We develop theoretical analysis to show that, given the maximal discriminators, optimizing the generator of D2GAN reduces to minimizing both KL and reverse KL divergences between data distribution and the distribution induced from the data generated by the generator, hence effectively avoiding the mode collapsing problem. We conduct extensive experiments on synthetic and real-world large-scale datasets (MNIST, CIFAR-10, STL-10, ImageNet), where we have made our best effort to compare our D2GAN with the latest state-of-the-art GAN’s variants in comprehensive qualitative and quantitative evaluations. The experimental results demonstrate the competitive and superior performance of our approach in generating good quality and diverse samples over baselines, and the capability of our method to scale up to ImageNet database. |
| Tasks | |
| Published | 2017-09-12 |
| URL | http://arxiv.org/abs/1709.03831v1 |
| http://arxiv.org/pdf/1709.03831v1.pdf | |
| PWC | https://paperswithcode.com/paper/dual-discriminator-generative-adversarial |
| Repo | https://github.com/alex98chen/testGAN |
| Framework | tf |
