Paper Group ANR 1431
Query-Focused Scenario Construction. A Unified Framework for Marketing Budget Allocation. Generative Models for Automatic Chemical Design. RETRO: Relation Retrofitting For In-Database Machine Learning on Textual Data. Accelerating Reinforcement Learning with Suboptimal Guidance. On sample complexity of neural networks. Turbo Learning Framework for …
Query-Focused Scenario Construction
| Title | Query-Focused Scenario Construction |
| Authors | Su Wang, Greg Durrett, Katrin Erk |
| Abstract | The news coverage of events often contains not one but multiple incompatible accounts of what happened. We develop a query-based system that extracts compatible sets of events (scenarios) from such data, formulated as one-class clustering. Our system incrementally evaluates each event’s compatibility with already selected events, taking order into account. We use synthetic data consisting of article mixtures for scalable training and evaluate our model on a new human-curated dataset of scenarios about real-world news topics. Stronger neural network models and harder synthetic training settings are both important to achieve high performance, and our final scenario construction system substantially outperforms baselines based on prior work. |
| Tasks | |
| Published | 2019-09-15 |
| URL | https://arxiv.org/abs/1909.06877v1 |
| https://arxiv.org/pdf/1909.06877v1.pdf | |
| PWC | https://paperswithcode.com/paper/query-focused-scenario-construction |
| Repo | |
| Framework | |
A Unified Framework for Marketing Budget Allocation
| Title | A Unified Framework for Marketing Budget Allocation |
| Authors | Kui Zhao, Junhao Hua, Ling Yan, Qi Zhang, Huan Xu, Cheng Yang |
| Abstract | While marketing budget allocation has been studied for decades in traditional business, nowadays online business brings much more challenges due to the dynamic environment and complex decision-making process. In this paper, we present a novel unified framework for marketing budget allocation. By leveraging abundant data, the proposed data-driven approach can help us to overcome the challenges and make more informed decisions. In our approach, a semi-black-box model is built to forecast the dynamic market response and an efficient optimization method is proposed to solve the complex allocation task. First, the response in each market-segment is forecasted by exploring historical data through a semi-black-box model, where the capability of logit demand curve is enhanced by neural networks. The response model reveals relationship between sales and marketing cost. Based on the learned model, budget allocation is then formulated as an optimization problem, and we design efficient algorithms to solve it in both continuous and discrete settings. Several kinds of business constraints are supported in one unified optimization paradigm, including cost upper bound, profit lower bound, or ROI lower bound. The proposed framework is easy to implement and readily to handle large-scale problems. It has been successfully applied to many scenarios in Alibaba Group. The results of both offline experiments and online A/B testing demonstrate its effectiveness. |
| Tasks | Decision Making |
| Published | 2019-02-04 |
| URL | https://arxiv.org/abs/1902.01128v3 |
| https://arxiv.org/pdf/1902.01128v3.pdf | |
| PWC | https://paperswithcode.com/paper/a-unified-framework-for-marketing-budget |
| Repo | |
| Framework | |
Generative Models for Automatic Chemical Design
| Title | Generative Models for Automatic Chemical Design |
| Authors | Daniel Schwalbe-Koda, Rafael Gómez-Bombarelli |
| Abstract | Materials discovery is decisive for tackling urgent challenges related to energy, the environment, health care and many others. In chemistry, conventional methodologies for innovation usually rely on expensive and incremental strategies to optimize properties from molecular structures. On the other hand, inverse approaches map properties to structures, thus expediting the design of novel useful compounds. In this chapter, we examine the way in which current deep generative models are addressing the inverse chemical discovery paradigm. We begin by revisiting early inverse design algorithms. Then, we introduce generative models for molecular systems and categorize them according to their architecture and molecular representation. Using this classification, we review the evolution and performance of important molecular generation schemes reported in the literature. Finally, we conclude highlighting the prospects and challenges of generative models as cutting edge tools in materials discovery. |
| Tasks | |
| Published | 2019-07-02 |
| URL | https://arxiv.org/abs/1907.01632v1 |
| https://arxiv.org/pdf/1907.01632v1.pdf | |
| PWC | https://paperswithcode.com/paper/generative-models-for-automatic-chemical |
| Repo | |
| Framework | |
RETRO: Relation Retrofitting For In-Database Machine Learning on Textual Data
| Title | RETRO: Relation Retrofitting For In-Database Machine Learning on Textual Data |
| Authors | Michael Günther, Maik Thiele, Wolfgang Lehner |
| Abstract | There are massive amounts of textual data residing in databases, valuable for many machine learning (ML) tasks. Since ML techniques depend on numerical input representations, word embeddings are increasingly utilized to convert symbolic representations such as text into meaningful numbers. However, a naive one-to-one mapping of each word in a database to a word embedding vector is not sufficient and would lead to poor accuracies in ML tasks. Thus, we argue to additionally incorporate the information given by the database schema into the embedding, e.g. which words appear in the same column or are related to each other. In this paper, we propose RETRO (RElational reTROfitting), a novel approach to learn numerical representations of text values in databases, capturing the best of both worlds, the rich information encoded by word embeddings and the relational information encoded by database tables. We formulate relation retrofitting as a learning problem and present an efficient algorithm solving it. We investigate the impact of various hyperparameters on the learning problem and derive good settings for all of them. Our evaluation shows that the proposed embeddings are ready-to-use for many ML tasks such as classification and regression and even outperform state-of-the-art techniques in integration tasks such as null value imputation and link prediction. |
| Tasks | Imputation, Link Prediction, Word Embeddings |
| Published | 2019-11-28 |
| URL | https://arxiv.org/abs/1911.12674v2 |
| https://arxiv.org/pdf/1911.12674v2.pdf | |
| PWC | https://paperswithcode.com/paper/retro-relation-retrofitting-for-in-database |
| Repo | |
| Framework | |
Accelerating Reinforcement Learning with Suboptimal Guidance
| Title | Accelerating Reinforcement Learning with Suboptimal Guidance |
| Authors | Eivind Bøhn, Signe Moe, Tor Arne Johansen |
| Abstract | Reinforcement Learning in domains with sparse rewards is a difficult problem, and a large part of the training process is often spent searching the state space in a more or less random fashion for any learning signals. For control problems, we often have some controller readily available which might be suboptimal but nevertheless solves the problem to some degree. This controller can be used to guide the initial exploration phase of the learning controller towards reward yielding states, reducing the time before refinement of a viable policy can be initiated. In our work, the agent is guided through an auxiliary behaviour cloning loss which is made conditional on a Q-filter, i.e. it is only applied in situations where the critic deems the guiding controller to be better than the agent. The Q-filter provides a natural way to adjust the guidance throughout the training process, allowing the agent to exceed the guiding controller in a manner that is adaptive to the task at hand and the proficiency of the guiding controller. The contribution of this paper lies in identifying shortcomings in previously proposed implementations of the Q-filter concept, and in suggesting some ways these issues can be mitigated. These modifications are tested on the OpenAI Gym Fetch environments, showing clear improvements in adaptivity and yielding increased performance in all robotic environments tested. |
| Tasks | |
| Published | 2019-11-21 |
| URL | https://arxiv.org/abs/1911.09391v1 |
| https://arxiv.org/pdf/1911.09391v1.pdf | |
| PWC | https://paperswithcode.com/paper/accelerating-reinforcement-learning-with |
| Repo | |
| Framework | |
On sample complexity of neural networks
| Title | On sample complexity of neural networks |
| Authors | Alexander Usvyatsov |
| Abstract | We consider functions defined by deep neural networks as definable objects in an o-miminal expansion of the real field, and derive an almost linear (in the number of weights) bound on sample complexity of such networks. |
| Tasks | |
| Published | 2019-10-24 |
| URL | https://arxiv.org/abs/1910.11080v1 |
| https://arxiv.org/pdf/1910.11080v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-sample-complexity-of-neural-networks |
| Repo | |
| Framework | |
Turbo Learning Framework for Human-Object Interactions Recognition and Human Pose Estimation
| Title | Turbo Learning Framework for Human-Object Interactions Recognition and Human Pose Estimation |
| Authors | Wei Feng, Wentao Liu, Tong Li, Jing Peng, Chen Qian, Xiaolin Hu |
| Abstract | Human-object interactions (HOI) recognition and pose estimation are two closely related tasks. Human pose is an essential cue for recognizing actions and localizing the interacted objects. Meanwhile, human action and their interacted objects’ localizations provide guidance for pose estimation. In this paper, we propose a turbo learning framework to perform HOI recognition and pose estimation simultaneously. First, two modules are designed to enforce message passing between the tasks, i.e. pose aware HOI recognition module and HOI guided pose estimation module. Then, these two modules form a closed loop to utilize the complementary information iteratively, which can be trained in an end-to-end manner. The proposed method achieves the state-of-the-art performance on two public benchmarks including Verbs in COCO (V-COCO) and HICO-DET datasets. |
| Tasks | Human-Object Interaction Detection, Pose Estimation |
| Published | 2019-03-15 |
| URL | http://arxiv.org/abs/1903.06355v1 |
| http://arxiv.org/pdf/1903.06355v1.pdf | |
| PWC | https://paperswithcode.com/paper/turbo-learning-framework-for-human-object |
| Repo | |
| Framework | |
An AI model for Rapid and Accurate Identification of Chemical Agents in Mass Casualty Incidents
| Title | An AI model for Rapid and Accurate Identification of Chemical Agents in Mass Casualty Incidents |
| Authors | Nicholas Boltin, Daniel Vu, Bethany Janos, Alyssa Shofner, Joan Culley, Homayoun Valafar |
| Abstract | In this report we examine the effectiveness of WISER in identification of a chemical culprit during a chemical based Mass Casualty Incident (MCI). We also evaluate and compare Binary Decision Tree (BDT) and Artificial Neural Networks (ANN) using the same experimental conditions as WISER. The reverse engineered set of Signs/Symptoms from the WISER application was used as the training set and 31,100 simulated patient records were used as the testing set. Three sets of simulated patient records were generated by 5%, 10% and 15% perturbation of the Signs/Symptoms of each chemical record. While all three methods achieved a 100% training accuracy, WISER, BDT and ANN produced performances in the range of: 1.8%-0%, 65%-26%, 67%-21% respectively. A preliminary investigation of dimensional reduction using ANN illustrated a dimensional collapse from 79 variables to 40 with little loss of classification performance. |
| Tasks | |
| Published | 2019-12-12 |
| URL | https://arxiv.org/abs/2001.09735v1 |
| https://arxiv.org/pdf/2001.09735v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-ai-model-for-rapid-and-accurate |
| Repo | |
| Framework | |
Interactive AI with a Theory of Mind
| Title | Interactive AI with a Theory of Mind |
| Authors | Mustafa Mert Çelikok, Tomi Peltola, Pedram Daee, Samuel Kaski |
| Abstract | Understanding each other is the key to success in collaboration. For humans, attributing mental states to others, the theory of mind, provides the crucial advantage. We argue for formulating human–AI interaction as a multi-agent problem, endowing AI with a computational theory of mind to understand and anticipate the user. To differentiate the approach from previous work, we introduce a categorisation of user modelling approaches based on the level of agency learnt in the interaction. We describe our recent work in using nested multi-agent modelling to formulate user models for multi-armed bandit based interactive AI systems, including a proof-of-concept user study. |
| Tasks | |
| Published | 2019-12-01 |
| URL | https://arxiv.org/abs/1912.05284v1 |
| https://arxiv.org/pdf/1912.05284v1.pdf | |
| PWC | https://paperswithcode.com/paper/interactive-ai-with-a-theory-of-mind |
| Repo | |
| Framework | |
Where is the Fake? Patch-Wise Supervised GANs for Texture Inpainting
| Title | Where is the Fake? Patch-Wise Supervised GANs for Texture Inpainting |
| Authors | Ahmed Ben Saad, Youssef Tamaazousti, Josselin Kherroubi, Alexis He |
| Abstract | We tackle the problem of texture inpainting where the input images are textures with missing values along with masks that indicate the zones that should be generated. Many works have been done in image inpainting with the aim to achieve global and local consistency. But these works still suffer from limitations when dealing with textures. In fact, the local information in the image to be completed needs to be used in order to achieve local continuities and visually realistic texture inpainting. For this, we propose a new segmentor discriminator that performs a patch-wise real/fake classification and is supervised by input masks. During training, it aims to locate the fake and thus backpropagates consistent signal to the generator. We tested our approach on the publicly available DTD dataset and showed that it achieves state-of-the-art performances and better deals with local consistency than existing methods. |
| Tasks | Image Inpainting |
| Published | 2019-11-06 |
| URL | https://arxiv.org/abs/1911.02274v2 |
| https://arxiv.org/pdf/1911.02274v2.pdf | |
| PWC | https://paperswithcode.com/paper/where-is-the-fake-patch-wise-supervised-gans |
| Repo | |
| Framework | |
Neural Execution of Graph Algorithms
| Title | Neural Execution of Graph Algorithms |
| Authors | Petar Veličković, Rex Ying, Matilde Padovano, Raia Hadsell, Charles Blundell |
| Abstract | Graph Neural Networks (GNNs) are a powerful representational tool for solving problems on graph-structured inputs. In almost all cases so far, however, they have been applied to directly recovering a final solution from raw inputs, without explicit guidance on how to structure their problem-solving. Here, instead, we focus on learning in the space of algorithms: we train several state-of-the-art GNN architectures to imitate individual steps of classical graph algorithms, parallel (breadth-first search, Bellman-Ford) as well as sequential (Prim’s algorithm). As graph algorithms usually rely on making discrete decisions within neighbourhoods, we hypothesise that maximisation-based message passing neural networks are best-suited for such objectives, and validate this claim empirically. We also demonstrate how learning in the space of algorithms can yield new opportunities for positive transfer between tasks—showing how learning a shortest-path algorithm can be substantially improved when simultaneously learning a reachability algorithm. |
| Tasks | |
| Published | 2019-10-23 |
| URL | https://arxiv.org/abs/1910.10593v2 |
| https://arxiv.org/pdf/1910.10593v2.pdf | |
| PWC | https://paperswithcode.com/paper/neural-execution-of-graph-algorithms |
| Repo | |
| Framework | |
On the usage of the probability integral transform to reduce the complexity of multi-way fuzzy decision trees in Big Data classification problems
| Title | On the usage of the probability integral transform to reduce the complexity of multi-way fuzzy decision trees in Big Data classification problems |
| Authors | Mikel Elkano, Mikel Uriz, Humberto Bustince, Mikel Galar |
| Abstract | We present a new distributed fuzzy partitioning method to reduce the complexity of multi-way fuzzy decision trees in Big Data classification problems. The proposed algorithm builds a fixed number of fuzzy sets for all variables and adjusts their shape and position to the real distribution of training data. A two-step process is applied : 1) transformation of the original distribution into a standard uniform distribution by means of the probability integral transform. Since the original distribution is generally unknown, the cumulative distribution function is approximated by computing the q-quantiles of the training set; 2) construction of a Ruspini strong fuzzy partition in the transformed attribute space using a fixed number of equally distributed triangular membership functions. Despite the aforementioned transformation, the definition of every fuzzy set in the original space can be recovered by applying the inverse cumulative distribution function (also known as quantile function). The experimental results reveal that the proposed methodology allows the state-of-the-art multi-way fuzzy decision tree (FMDT) induction algorithm to maintain classification accuracy with up to 6 million fewer leaves. |
| Tasks | |
| Published | 2019-02-28 |
| URL | http://arxiv.org/abs/1903.00345v1 |
| http://arxiv.org/pdf/1903.00345v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-usage-of-the-probability-integral |
| Repo | |
| Framework | |
Train One Get One Free: Partially Supervised Neural Network for Bug Report Duplicate Detection and Clustering
| Title | Train One Get One Free: Partially Supervised Neural Network for Bug Report Duplicate Detection and Clustering |
| Authors | Lahari Poddar, Leonardo Neves, William Brendel, Luis Marujo, Sergey Tulyakov, Pradeep Karuturi |
| Abstract | Tracking user reported bugs requires considerable engineering effort in going through many repetitive reports and assigning them to the correct teams. This paper proposes a neural architecture that can jointly (1) detect if two bug reports are duplicates, and (2) aggregate them into latent topics. Leveraging the assumption that learning the topic of a bug is a sub-task for detecting duplicates, we design a loss function that can jointly perform both tasks but needs supervision for only duplicate classification, achieving topic clustering in an unsupervised fashion. We use a two-step attention module that uses self-attention for topic clustering and conditional attention for duplicate detection. We study the characteristics of two types of real world datasets that have been marked for duplicate bugs by engineers and by non-technical annotators. The results demonstrate that our model not only can outperform state-of-the-art methods for duplicate classification on both cases, but can also learn meaningful latent clusters without additional supervision. |
| Tasks | |
| Published | 2019-03-29 |
| URL | http://arxiv.org/abs/1903.12431v2 |
| http://arxiv.org/pdf/1903.12431v2.pdf | |
| PWC | https://paperswithcode.com/paper/train-one-get-one-free-partially-supervised |
| Repo | |
| Framework | |
The efficacy of various machine learning models for multi-class classification of RNA-seq expression data
| Title | The efficacy of various machine learning models for multi-class classification of RNA-seq expression data |
| Authors | Sterling Ramroach, Melford John, Ajay Joshi |
| Abstract | Late diagnosis and high costs are key factors that negatively impact the care of cancer patients worldwide. Although the availability of biological markers for the diagnosis of cancer type is increasing, costs and reliability of tests currently present a barrier to the adoption of their routine use. There is a pressing need for accurate methods that enable early diagnosis and cover a broad range of cancers. The use of machine learning and RNA-seq expression analysis has shown promise in the classification of cancer type. However, research is inconclusive about which type of machine learning models are optimal. The suitability of five algorithms were assessed for the classification of 17 different cancer types. Each algorithm was fine-tuned and trained on the full array of 18,015 genes per sample, for 4,221 samples (75 % of the dataset). They were then tested with 1,408 samples (25 % of the dataset) for which cancer types were withheld to determine the accuracy of prediction. The results show that ensemble algorithms achieve 100% accuracy in the classification of 14 out of 17 types of cancer. The clustering and classification models, while faster than the ensembles, performed poorly due to the high level of noise in the dataset. When the features were reduced to a list of 20 genes, the ensemble algorithms maintained an accuracy above 95% as opposed to the clustering and classification models. |
| Tasks | |
| Published | 2019-08-19 |
| URL | https://arxiv.org/abs/1908.06817v1 |
| https://arxiv.org/pdf/1908.06817v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-efficacy-of-various-machine-learning |
| Repo | |
| Framework | |
Intelligent Wireless Sensor Nodes for Human Footstep Sound Classification for Security Application
| Title | Intelligent Wireless Sensor Nodes for Human Footstep Sound Classification for Security Application |
| Authors | Anand Kumar Mukhopadhyay, Naligala Moses Prabhakar, Divya Lakshmi Duggisetty, Indrajit Chakrabarti, Mrigank Sharad |
| Abstract | Sensor nodes present in a wireless sensor network (WSN) for security surveillance applications should preferably be small, energy-efficient and inexpensive with on-sensor computational abilities. An appropriate data processing scheme in the sensor node can help in reducing the power dissipation of the transceiver through compression of information to be communicated. In this paper, authors have attempted a simulation-based study of human footstep sound classification in natural surroundings using simple time-domain features. We used a spiking neural network (SNN), a computationally low weight classifier, derived from an artificial neural network (ANN), for classification. A classification accuracy greater than 85% is achieved using an SNN, degradation of ~5% as compared to ANN. The SNN scheme, along with the required feature extraction scheme, can be amenable to low power sub-threshold analog implementation. Results show that all analog implementation of the proposed SNN scheme can achieve significant power savings over the digital implementation of the same computing scheme and also over other conventional digital architectures using frequency-domain feature extraction and ANN-based classification. |
| Tasks | |
| Published | 2019-12-23 |
| URL | https://arxiv.org/abs/1912.10905v1 |
| https://arxiv.org/pdf/1912.10905v1.pdf | |
| PWC | https://paperswithcode.com/paper/intelligent-wireless-sensor-nodes-for-human |
| Repo | |
| Framework | |
