Paper Group ANR 1224
Machine learning for protein folding and dynamics. Reliable Weakly Supervised Learning: Maximize Gain and Maintain Safeness. The Power of Factorization Mechanisms in Local and Central Differential Privacy. Neural Machine Translation with Noisy Lexical Constraints. Meta-neural-network for Realtime and Passive Deep-learning-based Object Recognition. …
Machine learning for protein folding and dynamics
| Title | Machine learning for protein folding and dynamics |
| Authors | Frank Noé, Gianni De Fabritiis, Cecilia Clementi |
| Abstract | Many aspects of the study of protein folding and dynamics have been affected by the recent advances in machine learning. Methods for the prediction of protein structures from their sequences are now heavily based on machine learning tools. The way simulations are performed to explore the energy landscape of protein systems is also changing as force-fields are started to be designed by means of machine learning methods. These methods are also used to extract the essential information from large simulation datasets and to enhance the sampling of rare events such as folding/unfolding transitions. While significant challenges still need to be tackled, we expect these methods to play an important role on the study of protein folding and dynamics in the near future. We discuss here the recent advances on all these fronts and the questions that need to be addressed for machine learning approaches to become mainstream in protein simulation. |
| Tasks | |
| Published | 2019-11-22 |
| URL | https://arxiv.org/abs/1911.09811v1 |
| https://arxiv.org/pdf/1911.09811v1.pdf | |
| PWC | https://paperswithcode.com/paper/machine-learning-for-protein-folding-and |
| Repo | |
| Framework | |
Reliable Weakly Supervised Learning: Maximize Gain and Maintain Safeness
| Title | Reliable Weakly Supervised Learning: Maximize Gain and Maintain Safeness |
| Authors | Lan-Zhe Guo, Yu-Feng Li, Ming Li, Jin-Feng Yi, Bo-Wen Zhou, Zhi-Hua Zhou |
| Abstract | Weakly supervised data are widespread and have attracted much attention. However, since label quality is often difficult to guarantee, sometimes the use of weakly supervised data will lead to unsatisfactory performance, i.e., performance degradation or poor performance gains. Moreover, it is usually not feasible to manually increase the label quality, which results in weakly supervised learning being somewhat difficult to rely on. In view of this crucial issue, this paper proposes a simple and novel weakly supervised learning framework. We guide the optimization of label quality through a small amount of validation data, and to ensure the safeness of performance while maximizing performance gain. As validation set is a good approximation for describing generalization risk, it can effectively avoid the unsatisfactory performance caused by incorrect data distribution assumptions. We formalize this underlying consideration into a novel Bi-Level optimization and give an effective solution. Extensive experimental results verify that the new framework achieves impressive performance on weakly supervised learning with a small amount of validation data. |
| Tasks | |
| Published | 2019-04-22 |
| URL | http://arxiv.org/abs/1904.09743v1 |
| http://arxiv.org/pdf/1904.09743v1.pdf | |
| PWC | https://paperswithcode.com/paper/reliable-weakly-supervised-learning-maximize |
| Repo | |
| Framework | |
The Power of Factorization Mechanisms in Local and Central Differential Privacy
| Title | The Power of Factorization Mechanisms in Local and Central Differential Privacy |
| Authors | Alexander Edmonds, Aleksandar Nikolov, Jonathan Ullman |
| Abstract | We give new characterizations of the sample complexity of answering linear queries (statistical queries) in the local and central models of differential privacy: *In the non-interactive local model, we give the first approximate characterization of the sample complexity. Informally our bounds are tight to within polylogarithmic factors in the number of queries and desired accuracy. Our characterization extends to agnostic learning in the local model. *In the central model, we give a characterization of the sample complexity in the high-accuracy regime that is analogous to that of Nikolov, Talwar, and Zhang (STOC 2013), but is both quantitatively tighter and has a dramatically simpler proof. Our lower bounds apply equally to the empirical and population estimation problems. In both cases, our characterizations show that a particular factorization mechanism is approximately optimal, and the optimal sample complexity is bounded from above and below by well studied factorization norms of a matrix associated with the queries. |
| Tasks | |
| Published | 2019-11-19 |
| URL | https://arxiv.org/abs/1911.08339v1 |
| https://arxiv.org/pdf/1911.08339v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-power-of-factorization-mechanisms-in |
| Repo | |
| Framework | |
Neural Machine Translation with Noisy Lexical Constraints
| Title | Neural Machine Translation with Noisy Lexical Constraints |
| Authors | Huayang Li, Guoping Huang, Lemao Liu |
| Abstract | Lexically constrained decoding for machine translation has shown to be beneficial in previous studies. Unfortunately, constraints provided by users may contain mistakes in real-world situations. It is still an open question that how to manipulate these noisy constraints in such practical scenarios. We present a novel framework that treats constraints as external memories. In this soft manner, a mistaken constraint can be corrected. Experiments demonstrate that our approach can achieve substantial BLEU gains in handling noisy constraints. These results motivate us to apply the proposed approach on a new scenario where constraints are generated without the help of users. Experiments show that our approach can indeed improve the translation quality with the automatically generated constraints. |
| Tasks | Machine Translation |
| Published | 2019-08-13 |
| URL | https://arxiv.org/abs/1908.04664v1 |
| https://arxiv.org/pdf/1908.04664v1.pdf | |
| PWC | https://paperswithcode.com/paper/neural-machine-translation-with-noisy-lexical |
| Repo | |
| Framework | |
Meta-neural-network for Realtime and Passive Deep-learning-based Object Recognition
| Title | Meta-neural-network for Realtime and Passive Deep-learning-based Object Recognition |
| Authors | Jingkai Weng, Yujiang Ding, Chengbo Hu, Xue-feng Zhu, Bin Liang, Jing Yang, Jianchun Cheng |
| Abstract | Deep-learning recently show great success across disciplines yet conventionally require time-consuming computer processing or bulky-sized diffractive elements. Here we theoretically propose and experimentally demonstrate a purely-passive “meta-neural-network” with compactness and high-resolution for real-time recognizing complicated objects by analyzing acoustic scattering. We prove our meta-neural-network mimics standard neural network despite its small footprint, thanks to unique capability of its metamaterial unit cells, dubbed “meta-neurons”, to produce deep-subwavelength-distribution of discrete phase shift as learnable parameters during training. The resulting device exhibits the “intelligence” to perform desired tasks with potential to address the current trade-off between reducing device’s size, cost and energy consumption and increasing recognition speed and accuracy, showcased by an example of handwritten digit recognition. Our mechanism opens the route to new metamaterial-based deep-learning paradigms and enable conceptual devices such as smart transducers automatically analyzing signals, with far-reaching implications for acoustics, optics and related fields. |
| Tasks | Handwritten Digit Recognition, Object Recognition |
| Published | 2019-09-16 |
| URL | https://arxiv.org/abs/1909.07122v1 |
| https://arxiv.org/pdf/1909.07122v1.pdf | |
| PWC | https://paperswithcode.com/paper/meta-neural-network-for-realtime-and-passive |
| Repo | |
| Framework | |
A Generate-Validate Approach to Answering Questions about Qualitative Relationships
| Title | A Generate-Validate Approach to Answering Questions about Qualitative Relationships |
| Authors | Arindam Mitra, Chitta Baral, Aurgho Bhattacharjee, Ishan Shrivastava |
| Abstract | Qualitative relationships describe how increasing or decreasing one property (e.g. altitude) affects another (e.g. temperature). They are an important aspect of natural language question answering and are crucial for building chatbots or voice agents where one may enquire about qualitative relationships. Recently a dataset about question answering involving qualitative relationships has been proposed, and a few approaches to answer such questions have been explored, in the heart of which lies a semantic parser that converts the natural language input to a suitable logical form. A problem with existing semantic parsers is that they try to directly convert the input sentences to a logical form. Since the output language varies with each application, it forces the semantic parser to learn almost everything from scratch. In this paper, we show that instead of using a semantic parser to produce the logical form, if we apply the generate-validate framework i.e. generate a natural language description of the logical form and validate if the natural language description is followed from the input text, we get a better scope for transfer learning and our method outperforms the state-of-the-art by a large margin of 7.93%. |
| Tasks | Question Answering, Transfer Learning |
| Published | 2019-08-09 |
| URL | https://arxiv.org/abs/1908.03645v1 |
| https://arxiv.org/pdf/1908.03645v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-generate-validate-approach-to-answering |
| Repo | |
| Framework | |
TEQUILA: Temporal Question Answering over Knowledge Bases
| Title | TEQUILA: Temporal Question Answering over Knowledge Bases |
| Authors | Zhen Jia, Abdalghani Abujabal, Rishiraj Saha Roy, Jannik Stroetgen, Gerhard Weikum |
| Abstract | Question answering over knowledge bases (KB-QA) poses challenges in handling complex questions that need to be decomposed into sub-questions. An important case, addressed here, is that of temporal questions, where cues for temporal relations need to be discovered and handled. We present TEQUILA, an enabler method for temporal QA that can run on top of any KB-QA engine. TEQUILA has four stages. It detects if a question has temporal intent. It decomposes and rewrites the question into non-temporal sub-questions and temporal constraints. Answers to sub-questions are then retrieved from the underlying KB-QA engine. Finally, TEQUILA uses constraint reasoning on temporal intervals to compute final answers to the full question. Comparisons against state-of-the-art baselines show the viability of our method. |
| Tasks | Question Answering |
| Published | 2019-08-09 |
| URL | https://arxiv.org/abs/1908.03650v3 |
| https://arxiv.org/pdf/1908.03650v3.pdf | |
| PWC | https://paperswithcode.com/paper/tequila-temporal-question-answering-over |
| Repo | |
| Framework | |
Bidding in Spades
| Title | Bidding in Spades |
| Authors | Gal Cohensius, Reshef Meir, Nadav Oved, Roni Stern |
| Abstract | We present a Spades bidding algorithm that is superior to recreational human players and to publicly available bots. Like in Bridge, the game of Spades is composed of two independent phases, \textit{bidding} and \textit{playing}. This paper focuses on the bidding algorithm, since this phase holds a precise challenge: based on the input, choose the bid that maximizes the agent’s winning probability. Our \emph{Bidding-in-Spades} (BIS) algorithm heuristically determines the bidding strategy by comparing the expected utility of each possible bid. A major challenge is how to estimate these expected utilities. To this end, we propose a set of domain-specific heuristics, and then correct them via machine learning using data from real-world players. The \BIS algorithm we present can be attached to any playing algorithm. It beats rule-based bidding bots when all use the same playing component. When combined with a rule-based playing algorithm, it is superior to the average recreational human. |
| Tasks | |
| Published | 2019-12-24 |
| URL | https://arxiv.org/abs/1912.11323v2 |
| https://arxiv.org/pdf/1912.11323v2.pdf | |
| PWC | https://paperswithcode.com/paper/bidding-in-spades |
| Repo | |
| Framework | |
Repeated A/B Testing
| Title | Repeated A/B Testing |
| Authors | Nicolò Cesa-Bianchi, Tommaso R. Cesari, Yishay Mansour, Vianney Perchet |
| Abstract | A/B testing is of central importance in the industry, especially in the technology sector where companies run long sequences of A/B tests to optimize their products. Since the space of potential innovations is typically vast, the experimenter must make quick and good decisions without wasting too much time on a single A/B test in the sequence. In particular, discarding an innovation with a small benefit might be better in the long run than using many samples to precisely determine its value. In this work, we introduce a performance measure that captures this idea and design an efficient algorithm that performs almost as well as the best A/B strategy in a given set. As it turns out, a key technical difficulty that significantly affects the learning rates is the hardness of obtaining unbiased estimates of the strategy rewards. |
| Tasks | |
| Published | 2019-05-28 |
| URL | https://arxiv.org/abs/1905.11797v3 |
| https://arxiv.org/pdf/1905.11797v3.pdf | |
| PWC | https://paperswithcode.com/paper/repeated-ab-testing |
| Repo | |
| Framework | |
Using a Segmenting Description approach in Multiple Criteria Decision Aiding
| Title | Using a Segmenting Description approach in Multiple Criteria Decision Aiding |
| Authors | Milosz Kadzinski, Jan Badura, Jose Rui Figueira |
| Abstract | We propose a new method for analyzing a set of parameters in a multiple criteria ranking method. Unlike the existing techniques, we do not use any optimization technique, instead incorporating and extending a Segmenting Description approach. While considering a value-based preference disaggregation method, we demonstrate the usefulness of the introduced algorithm in a multi-purpose decision analysis exploiting a system of inequalities that models the Decision Maker’s preferences. Specifically, we discuss how it can be applied for verifying the consistency between the revealed and estimated preferences as well as for identifying the sources of potential incoherence. Moreover, we employ the method for conducting robustness analysis, i.e., discovering a set of all compatible parameter values and verifying the stability of suggested recommendation in view of multiplicity of feasible solutions. In addition, we make clear its suitability for generating arguments about the validity of outcomes and the role of particular criteria. We discuss the favorable characteristics of the Segmenting Description approach which enhance its suitability for use in Multiple Criteria Decision Aiding. These include keeping in memory an entire process of transforming a system of inequalities and avoiding the need for processing the inequalities contained in the basic system which is subsequently enriched with some hypothesis to be verified. The applicability of the proposed method is exemplified on a numerical study. |
| Tasks | |
| Published | 2019-03-05 |
| URL | http://arxiv.org/abs/1903.01923v1 |
| http://arxiv.org/pdf/1903.01923v1.pdf | |
| PWC | https://paperswithcode.com/paper/using-a-segmenting-description-approach-in |
| Repo | |
| Framework | |
On the Power and Limitations of Random Features for Understanding Neural Networks
| Title | On the Power and Limitations of Random Features for Understanding Neural Networks |
| Authors | Gilad Yehudai, Ohad Shamir |
| Abstract | Recently, a spate of papers have provided positive theoretical results for training over-parameterized neural networks (where the network size is larger than what is needed to achieve low error). The key insight is that with sufficient over-parameterization, gradient-based methods will implicitly leave some components of the network relatively unchanged, so the optimization dynamics will behave as if those components are essentially fixed at their initial random values. In fact, fixing these explicitly leads to the well-known approach of learning with random features. In other words, these techniques imply that we can successfully learn with neural networks, whenever we can successfully learn with random features. In this paper, we first review these techniques, providing a simple and self-contained analysis for one-hidden-layer networks. We then argue that despite the impressive positive results, random feature approaches are also inherently limited in what they can explain. In particular, we rigorously show that random features cannot be used to learn even a single ReLU neuron with standard Gaussian inputs, unless the network size (or magnitude of the weights) is exponentially large. Since a single neuron is learnable with gradient-based methods, we conclude that we are still far from a satisfying general explanation for the empirical success of neural networks. |
| Tasks | |
| Published | 2019-04-01 |
| URL | https://arxiv.org/abs/1904.00687v3 |
| https://arxiv.org/pdf/1904.00687v3.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-power-and-limitations-of-random |
| Repo | |
| Framework | |
Single-Channel Speech Separation with Auxiliary Speaker Embeddings
| Title | Single-Channel Speech Separation with Auxiliary Speaker Embeddings |
| Authors | Shuo Liu, Gil Keren, Björn Schuller |
| Abstract | We present a novel source separation model to decompose asingle-channel speech signal into two speech segments belonging to two different speakers. The proposed model is a neural network based on residual blocks, and uses learnt speaker embeddings created from additional clean context recordings of the two speakers as input to assist in attributing the different time-frequency bins to the two speakers. In experiments, we show that the proposed model yields good performance in the source separation task, and outperforms the state-of-the-art baselines. Specifically, separating speech from the challenging VoxCeleb dataset, the proposed model yields 4.79dB signal-to-distortion ratio, 8.44dB signal-to-artifacts ratio and 7.11dB signal-to-interference ratio. |
| Tasks | Speech Separation |
| Published | 2019-06-24 |
| URL | https://arxiv.org/abs/1906.09997v1 |
| https://arxiv.org/pdf/1906.09997v1.pdf | |
| PWC | https://paperswithcode.com/paper/single-channel-speech-separation-with |
| Repo | |
| Framework | |
Fast Hierarchical Neural Network for Feature Learning on Point Cloud
| Title | Fast Hierarchical Neural Network for Feature Learning on Point Cloud |
| Authors | Can Chen, Luca Zanotti Fragonara, Antonios Tsourdos |
| Abstract | The analyses relying on 3D point clouds are an utterly complex task, often involving million of points, but also requiring computationally efficient algorithms because of many real-time applications; e.g. autonomous vehicle. However, point clouds are intrinsically irregular and the points are sparsely distributed in a non-Euclidean space, which normally requires point-wise processing to achieve high performances. Although shared filter matrices and pooling layers in convolutional neural networks (CNNs) are capable of reducing the dimensionality of the problem and extracting high-level information simultaneously, grids and highly regular data format are required as input. In order to balance model performance and complexity, we introduce a novel neural network architecture exploiting local features from a manually subsampled point set. In our network, a recursive farthest point sampling method is firstly applied to efficiently cover the entire point set. Successively, we employ the k-nearest neighbours (knn) algorithm to gather local neighbourhood for each group of the subsampled points. Finally, a multiple layer perceptron (MLP) is applied on the subsampled points and edges that connect corresponding point and neighbours to extract local features. The architecture has been tested for both shape classification and segmentation using the ModelNet40 and ShapeNet part datasets, in order to show that the network achieves the best trade-off in terms of competitive performance when compared to other state-of-the-art algorithms. |
| Tasks | |
| Published | 2019-06-10 |
| URL | https://arxiv.org/abs/1906.04117v1 |
| https://arxiv.org/pdf/1906.04117v1.pdf | |
| PWC | https://paperswithcode.com/paper/fast-hierarchical-neural-network-for-feature |
| Repo | |
| Framework | |
Fast and Scalable Estimator for Sparse and Unit-Rank Higher-Order Regression Models
| Title | Fast and Scalable Estimator for Sparse and Unit-Rank Higher-Order Regression Models |
| Authors | Jiaqi Zhang, Beilun Wang |
| Abstract | Because tensor data appear more and more frequently in various scientific researches and real-world applications, analyzing the relationship between tensor features and the univariate outcome becomes an elementary task in many fields. To solve this task, we propose \underline{Fa}st \underline{S}parse \underline{T}ensor \underline{R}egression model (FasTR) based on so-called unit-rank CANDECOMP/PARAFAC decomposition. FasTR first decomposes the tensor coefficient into component vectors and then estimates each vector with $\ell_1$ regularized regression. Because of the independence of component vectors, FasTR is able to solve in a parallel way and the time complexity is proved to be superior to previous models. We evaluate the performance of FasTR on several simulated datasets and a real-world fMRI dataset. Experiment results show that, compared with four baseline models, in every case, FasTR can compute a better solution within less time. |
| Tasks | |
| Published | 2019-11-29 |
| URL | https://arxiv.org/abs/1912.01450v1 |
| https://arxiv.org/pdf/1912.01450v1.pdf | |
| PWC | https://paperswithcode.com/paper/fast-and-scalable-estimator-for-sparse-and |
| Repo | |
| Framework | |
The Role of Cooperation in Responsible AI Development
| Title | The Role of Cooperation in Responsible AI Development |
| Authors | Amanda Askell, Miles Brundage, Gillian Hadfield |
| Abstract | In this paper, we argue that competitive pressures could incentivize AI companies to underinvest in ensuring their systems are safe, secure, and have a positive social impact. Ensuring that AI systems are developed responsibly may therefore require preventing and solving collective action problems between companies. We note that there are several key factors that improve the prospects for cooperation in collective action problems. We use this to identify strategies to improve the prospects for industry cooperation on the responsible development of AI. |
| Tasks | |
| Published | 2019-07-10 |
| URL | https://arxiv.org/abs/1907.04534v1 |
| https://arxiv.org/pdf/1907.04534v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-role-of-cooperation-in-responsible-ai |
| Repo | |
| Framework | |
