Paper Group ANR 129
Metaphoric Paraphrase Generation. Integrating Acting, Planning and Learning in Hierarchical Operational Models. Distributed function estimation: adaptation using minimal communication. The Engagement-Diversity Connection: Evidence from a Field Experiment on Spotify. TrojanNet: Embedding Hidden Trojan Horse Models in Neural Networks. Model Reuse wit …
Metaphoric Paraphrase Generation
| Title | Metaphoric Paraphrase Generation |
| Authors | Kevin Stowe, Leonardo Ribeiro, Iryna Gurevych |
| Abstract | This work describes the task of metaphoric paraphrase generation, in which we are given a literal sentence and are charged with generating a metaphoric paraphrase. We propose two different models for this task: a lexical replacement baseline and a novel sequence to sequence model, ‘metaphor masking’, that generates free metaphoric paraphrases. We use crowdsourcing to evaluate our results, as well as developing an automatic metric for evaluating metaphoric paraphrases. We show that while the lexical replacement baseline is capable of producing accurate paraphrases, they often lack metaphoricity, while our metaphor masking model excels in generating metaphoric sentences while performing nearly as well with regard to fluency and paraphrase quality. |
| Tasks | Paraphrase Generation |
| Published | 2020-02-28 |
| URL | https://arxiv.org/abs/2002.12854v1 |
| https://arxiv.org/pdf/2002.12854v1.pdf | |
| PWC | https://paperswithcode.com/paper/metaphoric-paraphrase-generation |
| Repo | |
| Framework | |
Integrating Acting, Planning and Learning in Hierarchical Operational Models
| Title | Integrating Acting, Planning and Learning in Hierarchical Operational Models |
| Authors | Sunandita Patra, James Mason, Amit Kumar, Malik Ghallab, Paolo Traverso, Dana Nau |
| Abstract | We present new planning and learning algorithms for RAE, the Refinement Acting Engine. RAE uses hierarchical operational models to perform tasks in dynamically changing environments. Our planning procedure, UPOM, does a UCT-like search in the space of operational models in order to find a near-optimal method to use for the task and context at hand. Our learning strategies acquire, from online acting experiences and/or simulated planning results, a mapping from decision contexts to method instances as well as a heuristic function to guide UPOM. Our experimental results show that UPOM and our learning strategies significantly improve RAE’s performance in four test domains using two different metrics: efficiency and success ratio. |
| Tasks | |
| Published | 2020-03-09 |
| URL | https://arxiv.org/abs/2003.03932v1 |
| https://arxiv.org/pdf/2003.03932v1.pdf | |
| PWC | https://paperswithcode.com/paper/integrating-acting-planning-and-learning-in |
| Repo | |
| Framework | |
Distributed function estimation: adaptation using minimal communication
| Title | Distributed function estimation: adaptation using minimal communication |
| Authors | Botond Szabo, Harry van Zanten |
| Abstract | We investigate whether in a distributed setting, adaptive estimation of a smooth function at the optimal rate is possible under minimal communication. It turns out that the answer depends on the risk considered and on the number of servers over which the procedure is distributed. We show that for the $L_\infty$-risk, adaptively obtaining optimal rates under minimal communication is not possible. For the $L_2$-risk, it is possible over a range of regularities that depends on the relation between the number of local servers and the total sample size. |
| Tasks | |
| Published | 2020-03-28 |
| URL | https://arxiv.org/abs/2003.12838v1 |
| https://arxiv.org/pdf/2003.12838v1.pdf | |
| PWC | https://paperswithcode.com/paper/distributed-function-estimation-adaptation |
| Repo | |
| Framework | |
The Engagement-Diversity Connection: Evidence from a Field Experiment on Spotify
| Title | The Engagement-Diversity Connection: Evidence from a Field Experiment on Spotify |
| Authors | David Holtz, Benjamin Carterette, Praveen Chandar, Zahra Nazari, Henriette Cramer, Sinan Aral |
| Abstract | It remains unknown whether personalized recommendations increase or decrease the diversity of content people consume. We present results from a randomized field experiment on Spotify testing the effect of personalized recommendations on consumption diversity. In the experiment, both control and treatment users were given podcast recommendations, with the sole aim of increasing podcast consumption. Treatment users’ recommendations were personalized based on their music listening history, whereas control users were recommended popular podcasts among users in their demographic group. We find that, on average, the treatment increased podcast streams by 28.90%. However, the treatment also decreased the average individual-level diversity of podcast streams by 11.51%, and increased the aggregate diversity of podcast streams by 5.96%, indicating that personalized recommendations have the potential to create patterns of consumption that are homogenous within and diverse across users, a pattern reflecting Balkanization. Our results provide evidence of an “engagement-diversity trade-off” when recommendations are optimized solely to drive consumption: while personalized recommendations increase user engagement, they also affect the diversity of consumed content. This shift in consumption diversity can affect user retention and lifetime value, and impact the optimal strategy for content producers. We also observe evidence that our treatment affected streams from sections of Spotify’s app not directly affected by the experiment, suggesting that exposure to personalized recommendations can affect the content that users consume organically. We believe these findings highlight the need for academics and practitioners to continue investing in personalization methods that explicitly take into account the diversity of content recommended. |
| Tasks | |
| Published | 2020-03-17 |
| URL | https://arxiv.org/abs/2003.08203v1 |
| https://arxiv.org/pdf/2003.08203v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-engagement-diversity-connection-evidence |
| Repo | |
| Framework | |
TrojanNet: Embedding Hidden Trojan Horse Models in Neural Networks
| Title | TrojanNet: Embedding Hidden Trojan Horse Models in Neural Networks |
| Authors | Chuan Guo, Ruihan Wu, Kilian Q. Weinberger |
| Abstract | The complexity of large-scale neural networks can lead to poor understanding of their internal details. We show that this opaqueness provides an opportunity for adversaries to embed unintended functionalities into the network in the form of Trojan horses. Our novel framework hides the existence of a Trojan network with arbitrary desired functionality within a benign transport network. We prove theoretically that the Trojan network’s detection is computationally infeasible and demonstrate empirically that the transport network does not compromise its disguise. Our paper exposes an important, previously unknown loophole that could potentially undermine the security and trustworthiness of machine learning. |
| Tasks | |
| Published | 2020-02-24 |
| URL | https://arxiv.org/abs/2002.10078v1 |
| https://arxiv.org/pdf/2002.10078v1.pdf | |
| PWC | https://paperswithcode.com/paper/trojannet-embedding-hidden-trojan-horse |
| Repo | |
| Framework | |
Model Reuse with Reduced Kernel Mean Embedding Specification
| Title | Model Reuse with Reduced Kernel Mean Embedding Specification |
| Authors | Xi-Zhu Wu, Wenkai Xu, Song Liu, Zhi-Hua Zhou |
| Abstract | Given a publicly available pool of machine learning models constructed for various tasks, when a user plans to build a model for her own machine learning application, is it possible to build upon models in the pool such that the previous efforts on these existing models can be reused rather than starting from scratch? Here, a grand challenge is how to find models that are helpful for the current application, without accessing the raw training data for the models in the pool. In this paper, we present a two-phase framework. In the upload phase, when a model is uploading into the pool, we construct a reduced kernel mean embedding (RKME) as a specification for the model. Then in the deployment phase, the relatedness of the current task and pre-trained models will be measured based on the value of the RKME specification. Theoretical results and extensive experiments validate the effectiveness of our approach. |
| Tasks | |
| Published | 2020-01-20 |
| URL | https://arxiv.org/abs/2001.07135v1 |
| https://arxiv.org/pdf/2001.07135v1.pdf | |
| PWC | https://paperswithcode.com/paper/model-reuse-with-reduced-kernel-mean |
| Repo | |
| Framework | |
Concept Embedding for Information Retrieval
| Title | Concept Embedding for Information Retrieval |
| Authors | Karam Abdulahhad |
| Abstract | Concepts are used to solve the term-mismatch problem. However, we need an effective similarity measure between concepts. Word embedding presents a promising solution. We present in this study three approaches to build concepts vectors based on words vectors. We use a vector-based measure to estimate inter-concepts similarity. Our experiments show promising results. Furthermore, words and concepts become comparable. This could be used to improve conceptual indexing process. |
| Tasks | Information Retrieval |
| Published | 2020-02-01 |
| URL | https://arxiv.org/abs/2002.01071v1 |
| https://arxiv.org/pdf/2002.01071v1.pdf | |
| PWC | https://paperswithcode.com/paper/concept-embedding-for-information-retrieval |
| Repo | |
| Framework | |
Using Machine Learning to Speed Up and Improve Calorimeter R&D
| Title | Using Machine Learning to Speed Up and Improve Calorimeter R&D |
| Authors | Fedor Ratnikov |
| Abstract | Design of new experiments, as well as upgrade of ongoing ones, is a continuous process in the experimental high energy physics. Since the best solution is a trade-off between different kinds of limitations, a quick turn over is necessary to evaluate physics performance for different techniques in different configurations. Two typical problems which slow down evaluation of physics performance for particular approaches to calorimeter detector technologies and configurations are: - Emulating particular detector properties including raw detector response together with a signal processing chain to adequately simulate a calorimeter response for different signal and background conditions. This includes combining detector properties obtained from the general Geant simulation with properties obtained from different kinds of bench and beam tests of detector and electronics prototypes. - Building an adequate reconstruction algorithm for physics reconstruction of the detector response which is reasonably tuned to extract the most of the performance provided by the given detector configuration. Being approached from the first principles, both problems require significant development efforts. Fortunately, both problems may be addressed by using modern machine learning approaches, that allow a combination of available details of the detector techniques into corresponding higher level physics performance in a semi-automated way. In this paper, we discuss the use of advanced machine learning techniques to speed up and improve the precision of the detector development and optimisation cycle, with an emphasis on the experience and practical results obtained by applying this approach to epitomising the electromagnetic calorimeter design as a part of the upgrade project for the LHCb detector at LHC. |
| Tasks | |
| Published | 2020-03-27 |
| URL | https://arxiv.org/abs/2003.12440v1 |
| https://arxiv.org/pdf/2003.12440v1.pdf | |
| PWC | https://paperswithcode.com/paper/using-machine-learning-to-speed-up-and |
| Repo | |
| Framework | |
Improving IoT Analytics through Selective Edge Execution
| Title | Improving IoT Analytics through Selective Edge Execution |
| Authors | A. Galanopoulos, A. G. Tasiopoulos, G. Iosifidis, T. Salonidis, D. J. Leith |
| Abstract | A large number of emerging IoT applications rely on machine learning routines for analyzing data. Executing such tasks at the user devices improves response time and economizes network resources. However, due to power and computing limitations, the devices often cannot support such resource-intensive routines and fail to accurately execute the analytics. In this work, we propose to improve the performance of analytics by leveraging edge infrastructure. We devise an algorithm that enables the IoT devices to execute their routines locally; and then outsource them to cloudlet servers, only if they predict they will gain a significant performance improvement. It uses an approximate dual subgradient method, making minimal assumptions about the statistical properties of the system’s parameters. Our analysis demonstrates that our proposed algorithm can intelligently leverage the cloudlet, adapting to the service requirements. |
| Tasks | |
| Published | 2020-03-07 |
| URL | https://arxiv.org/abs/2003.03588v1 |
| https://arxiv.org/pdf/2003.03588v1.pdf | |
| PWC | https://paperswithcode.com/paper/improving-iot-analytics-through-selective |
| Repo | |
| Framework | |
Estimating Latent Demand of Shared Mobility through Censored Gaussian Processes
| Title | Estimating Latent Demand of Shared Mobility through Censored Gaussian Processes |
| Authors | Daniele Gammelli, Inon Peled, Filipe Rodrigues, Dario Pacino, Haci A. Kurtaran, Francisco C. Pereira |
| Abstract | Transport demand is highly dependent on supply, especially for shared transport services where availability is often limited. As observed demand cannot be higher than available supply, historical transport data typically represents a biased, or censored, version of the true underlying demand pattern. Without explicitly accounting for this inherent distinction, predictive models of demand would necessarily represent a biased version of true demand, thus less effectively predicting the needs of service users. To counter this problem, we propose a general method for censorship-aware demand modeling, for which we devise a censored likelihood function. We apply this method to the task of shared mobility demand prediction by incorporating the censored likelihood within a Gaussian Process model, which can flexibly approximate arbitrary functional forms. Experiments on artificial and real-world datasets show how taking into account the limiting effect of supply on demand is essential in the process of obtaining an unbiased predictive model of user demand behavior. |
| Tasks | Gaussian Processes |
| Published | 2020-01-21 |
| URL | https://arxiv.org/abs/2001.07402v2 |
| https://arxiv.org/pdf/2001.07402v2.pdf | |
| PWC | https://paperswithcode.com/paper/estimating-latent-demand-of-shared-mobility |
| Repo | |
| Framework | |
Creating Synthetic Datasets via Evolution for Neural Program Synthesis
| Title | Creating Synthetic Datasets via Evolution for Neural Program Synthesis |
| Authors | Alexander Suh, Yuval Timen |
| Abstract | Program synthesis is the task of automatically generating a program consistent with a given specification. A natural way to specify programs is to provide examples of desired input-output behavior, and many current program synthesis approaches have achieved impressive results after training on randomly generated input-output examples. However, recent work has discovered that some of these approaches generalize poorly to data distributions different from that of the randomly generated examples. We show that this problem applies to other state-of-the-art approaches as well and that current methods to counteract this problem are insufficient. We then propose a new, adversarial approach to control the bias of synthetic data distributions and show that it outperforms current approaches. |
| Tasks | Program Synthesis |
| Published | 2020-03-23 |
| URL | https://arxiv.org/abs/2003.10485v1 |
| https://arxiv.org/pdf/2003.10485v1.pdf | |
| PWC | https://paperswithcode.com/paper/creating-synthetic-datasets-via-evolution-for |
| Repo | |
| Framework | |
TF-Coder: Program Synthesis for Tensor Manipulations
| Title | TF-Coder: Program Synthesis for Tensor Manipulations |
| Authors | Kensen Shi, David Bieber, Rishabh Singh |
| Abstract | The success and popularity of deep learning is on the rise, partially due to powerful deep learning frameworks such as TensorFlow and PyTorch that make it easier to develop deep learning models. However, these libraries also come with steep learning curves, since programming in these frameworks is quite different from traditional imperative programming with explicit loops and conditionals. In this work, we present a tool called TF-Coder for programming by example in TensorFlow. TF-Coder uses a bottom-up weighted enumerative search, with value-based pruning of equivalent expressions and flexible type- and value-based filtering to ensure that expressions adhere to various requirements imposed by the TensorFlow library. We also train models that predict TensorFlow operations from features of the input and output tensors and natural language descriptions of tasks, and use the models to prioritize relevant operations during the search. TF-Coder solves 63 of 70 real-world tasks within 5 minutes, often finding solutions that are simpler than those written by TensorFlow experts. |
| Tasks | Program Synthesis |
| Published | 2020-03-19 |
| URL | https://arxiv.org/abs/2003.09040v1 |
| https://arxiv.org/pdf/2003.09040v1.pdf | |
| PWC | https://paperswithcode.com/paper/tf-coder-program-synthesis-for-tensor |
| Repo | |
| Framework | |
Communication-Efficient Decentralized Learning with Sparsification and Adaptive Peer Selection
| Title | Communication-Efficient Decentralized Learning with Sparsification and Adaptive Peer Selection |
| Authors | Zhenheng Tang, Shaohuai Shi, Xiaowen Chu |
| Abstract | Distributed learning techniques such as federated learning have enabled multiple workers to train machine learning models together to reduce the overall training time. However, current distributed training algorithms (centralized or decentralized) suffer from the communication bottleneck on multiple low-bandwidth workers (also on the server under the centralized architecture). Although decentralized algorithms generally have lower communication complexity than the centralized counterpart, they still suffer from the communication bottleneck for workers with low network bandwidth. To deal with the communication problem while being able to preserve the convergence performance, we introduce a novel decentralized training algorithm with the following key features: 1) It does not require a parameter server to maintain the model during training, which avoids the communication pressure on any single peer. 2) Each worker only needs to communicate with a single peer at each communication round with a highly compressed model, which can significantly reduce the communication traffic on the worker. We theoretically prove that our sparsification algorithm still preserves convergence properties. 3) Each worker dynamically selects its peer at different communication rounds to better utilize the bandwidth resources. We conduct experiments with convolutional neural networks on 32 workers to verify the effectiveness of our proposed algorithm compared to seven existing methods. Experimental results show that our algorithm significantly reduces the communication traffic and generally select relatively high bandwidth peers. |
| Tasks | |
| Published | 2020-02-22 |
| URL | https://arxiv.org/abs/2002.09692v1 |
| https://arxiv.org/pdf/2002.09692v1.pdf | |
| PWC | https://paperswithcode.com/paper/communication-efficient-decentralized-1 |
| Repo | |
| Framework | |
Evaluating Sequence-to-Sequence Learning Models for If-Then Program Synthesis
| Title | Evaluating Sequence-to-Sequence Learning Models for If-Then Program Synthesis |
| Authors | Dhairya Dalal, Byron V. Galbraith |
| Abstract | Implementing enterprise process automation often requires significant technical expertise and engineering effort. It would be beneficial for non-technical users to be able to describe a business process in natural language and have an intelligent system generate the workflow that can be automatically executed. A building block of process automations are If-Then programs. In the consumer space, sites like IFTTT and Zapier allow users to create automations by defining If-Then programs using a graphical interface. We explore the efficacy of modeling If-Then programs as a sequence learning task. We find Seq2Seq approaches have high potential (performing strongly on the Zapier recipes) and can serve as a promising approach to more complex program synthesis challenges. |
| Tasks | Program Synthesis |
| Published | 2020-02-10 |
| URL | https://arxiv.org/abs/2002.03485v1 |
| https://arxiv.org/pdf/2002.03485v1.pdf | |
| PWC | https://paperswithcode.com/paper/evaluating-sequence-to-sequence-learning |
| Repo | |
| Framework | |
Unsupervised Program Synthesis for Images using Tree-Structured LSTM
| Title | Unsupervised Program Synthesis for Images using Tree-Structured LSTM |
| Authors | Chenghui Zhou, Chun-Liang Li, Barnabas Poczos |
| Abstract | Program synthesis has recently emerged as a promising approach to the image parsing task. However, most prior works have relied on supervised learning methods, which require ground truth programs for each training image. We present an unsupervised learning algorithm that can parse constructive solid geometry (CSG) images into context-free grammar with a non-differentiable renderer. We propose a grammar-encoded tree LSTM to effectively constrain our search space by leveraging the structure of the context-free grammar while handling the non-differentiable renderer via REINFORCE and encouraging the exploration by regularizing the objective with an entropy term. Instead of using simple Monte Carlo sampling, we propose a lower-variance entropy estimator with sampling without replacement for effective exploration. We demonstrate the effectiveness of the proposed algorithm on a synthetic 2D CSG dataset, which outperforms baseline models by a large margin. |
| Tasks | Program Synthesis |
| Published | 2020-01-27 |
| URL | https://arxiv.org/abs/2001.10119v1 |
| https://arxiv.org/pdf/2001.10119v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-program-synthesis-for-images |
| Repo | |
| Framework | |
