Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

"Topic": models, code, and papers

Detection and Classification of mental illnesses on social media using RoBERTa

Nov 23, 2020
Ankit Murarka, Balaji Radhakrishnan, Sushma Ravichandran

Given the current social distancing regulations across the world, social media has become the primary mode of communication for most people. This has resulted in the isolation of many people suffering from mental illnesses who are unable to receive assistance in person. They have increasingly turned to social media to express themselves and to look for guidance in dealing with their illnesses. Keeping this in mind, we propose a solution to detect and classify mental illness posts on social media thereby enabling users to seek appropriate help. In this work, we detect and classify five prominent kinds of mental illnesses: depression, anxiety, bipolar disorder, ADHD and PTSD by analyzing unstructured user data on social media platforms. In addition, we are sharing a new high-quality dataset to drive research on this topic. We believe that our work is the first multi-class model that uses a Transformer-based architecture such as RoBERTa to analyze people's emotions and psychology. We also demonstrate how we stress-test our model using behavioral testing. With this research, we hope to be able to contribute to the public health system by automating some of the detection and classification process.

* 8 pages, 1 figure, 6 tables 

  Access Paper or Ask Questions

AI Governance for Businesses

Nov 20, 2020
Johannes Schneider, Rene Abraham, Christian Meske

Artificial Intelligence (AI) governance regulates the exercise of authority and control over the management of AI. It aims at leveraging AI through effective use of data and minimization of AI-related cost and risk. While topics such as AI governance and AI ethics are thoroughly discussed on a theoretical, philosophical, societal and regulatory level, there is limited work on AI governance targeted to companies and corporations. This work views AI products as systems, where key functionality is delivered by machine learning (ML) models leveraging (training) data. We derive a conceptual framework by synthesizing literature on AI and related fields such as ML. Our framework decomposes AI governance into governance of data, (ML) models and (AI) systems along four dimensions. It relates to existing IT and data governance frameworks and practices. It can be adopted by practitioners and academics alike. For practitioners the synthesis of mainly research papers, but also practitioner publications and publications of regulatory bodies provides a valuable starting point to implement AI governance, while for academics the paper highlights a number of areas of AI governance that deserve more attention.

  Access Paper or Ask Questions

Sketch-Inspector: a Deep Mixture Model for High-Quality Sketch Generation of Cats

Nov 09, 2020
Yunkui Pang, Zhiqing Pan, Ruiyang Sun, Shuchong Wang

With the involvement of artificial intelligence (AI), sketches can be automatically generated under certain topics. Even though breakthroughs have been made in previous studies in this area, a relatively high proportion of the generated figures are too abstract to recognize, which illustrates that AIs fail to learn the general pattern of the target object when drawing. This paper posits that supervising the process of stroke generation can lead to a more accurate sketch interpretation. Based on that, a sketch generating system with an assistant convolutional neural network (CNN) predictor to suggest the shape of the next stroke is presented in this paper. In addition, a CNN-based discriminator is introduced to judge the recognizability of the end product. Since the base-line model is ineffective at generating multi-class sketches, we restrict the model to produce one category. Because the image of a cat is easy to identify, we consider cat sketches selected from the QuickDraw data set. This paper compares the proposed model with the original Sketch-RNN on 75K human-drawn cat sketches. The result indicates that our model produces sketches with higher quality than human's sketches.

* 12 pages, 7 figures, ISVC 2020 accepted 

  Access Paper or Ask Questions

Beyond Marginal Uncertainty: How Accurately can Bayesian Regression Models Estimate Posterior Predictive Correlations?

Nov 06, 2020
Chaoqi Wang, Shengyang Sun, Roger Grosse

While uncertainty estimation is a well-studied topic in deep learning, most such work focuses on marginal uncertainty estimates, i.e. the predictive mean and variance at individual input locations. But it is often more useful to estimate predictive correlations between the function values at different input locations. In this paper, we consider the problem of benchmarking how accurately Bayesian models can estimate predictive correlations. We first consider a downstream task which depends on posterior predictive correlations: transductive active learning (TAL). We find that TAL makes better use of models' uncertainty estimates than ordinary active learning, and recommend this as a benchmark for evaluating Bayesian models. Since TAL is too expensive and indirect to guide development of algorithms, we introduce two metrics which more directly evaluate the predictive correlations and which can be computed efficiently: meta-correlations (i.e. the correlations between the models correlation estimates and the true values), and cross-normalized likelihoods (XLL). We validate these metrics by demonstrating their consistency with TAL performance and obtain insights about the relative performance of current Bayesian neural net and Gaussian process models.

  Access Paper or Ask Questions

Revisiting LSTM Networks for Semi-Supervised Text Classification via Mixed Objective Function

Sep 08, 2020
Devendra Singh Sachan, Manzil Zaheer, Ruslan Salakhutdinov

In this paper, we study bidirectional LSTM network for the task of text classification using both supervised and semi-supervised approaches. Several prior works have suggested that either complex pretraining schemes using unsupervised methods such as language modeling (Dai and Le 2015; Miyato, Dai, and Goodfellow 2016) or complicated models (Johnson and Zhang 2017) are necessary to achieve a high classification accuracy. However, we develop a training strategy that allows even a simple BiLSTM model, when trained with cross-entropy loss, to achieve competitive results compared with more complex approaches. Furthermore, in addition to cross-entropy loss, by using a combination of entropy minimization, adversarial, and virtual adversarial losses for both labeled and unlabeled data, we report state-of-the-art results for text classification task on several benchmark datasets. In particular, on the ACL-IMDB sentiment analysis and AG-News topic classification datasets, our method outperforms current approaches by a substantial margin. We also show the generality of the mixed objective function by improving the performance on relation extraction task.

* Published at AAAI 2019 

  Access Paper or Ask Questions

Configuration Learning in Underwater Optical Links

Aug 03, 2020
Xueyuan Zhao, Zhuoran Qi, Dario Pompili

A new research problem named configuration learning is described in this work. A novel algorithm is proposed to address the configuration learning problem. The configuration learning problem is defined to be the optimization of the Machine Learning (ML) classifier to maximize the ML performance metric optimizing the transmitter configuration in the signal processing/communication systems. Specifically, this configuration learning problem is investigated in an underwater optical communication system with signal processing performance metric of the physical-layer communication throughput. A novel algorithm is proposed to perform the configuration learning by alternating optimization of key design parameters and switching between several Recurrent Neural Network (RNN) classifiers dependant on the learning objective. The proposed ML algorithm is validated with the datasets of an underwater optical communication system and is compared with competing ML algorithms. Performance results indicate that the proposal outperforms the competing algorithms for binary and multi-class configuration learning in underwater optical communication datasets. The proposed configuration learning framework can be further investigated and applied to a broad range of topics in signal processing and communications.

  Access Paper or Ask Questions

Exploiting Visual Semantic Reasoning for Video-Text Retrieval

Jun 16, 2020
Zerun Feng, Zhimin Zeng, Caili Guo, Zheng Li

Video retrieval is a challenging research topic bridging the vision and language areas and has attracted broad attention in recent years. Previous works have been devoted to representing videos by directly encoding from frame-level features. In fact, videos consist of various and abundant semantic relations to which existing methods pay less attention. To address this issue, we propose a Visual Semantic Enhanced Reasoning Network (ViSERN) to exploit reasoning between frame regions. Specifically, we consider frame regions as vertices and construct a fully-connected semantic correlation graph. Then, we perform reasoning by novel random walk rule-based graph convolutional networks to generate region features involved with semantic relations. With the benefit of reasoning, semantic interactions between regions are considered, while the impact of redundancy is suppressed. Finally, the region features are aggregated to form frame-level features for further encoding to measure video-text similarity. Extensive experiments on two public benchmark datasets validate the effectiveness of our method by achieving state-of-the-art performance due to the powerful semantic reasoning.

* Accepted by IJCAI 2020. SOLE copyright holder is IJCAI (International Joint Conferences on Artificial Intelligence), all rights reserved. 

  Access Paper or Ask Questions

Are We Hungry for 3D LiDAR Data for Semantic Segmentation?

Jun 08, 2020
Biao Gao, Yancheng Pan, Chengkun Li, Sibo Geng, Huijing Zhao

3D LiDAR semantic segmentation is a pivotal task that is widely involved in many applications, such as autonomous driving and robotics. Studies of 3D LiDAR semantic segmentation have recently achieved considerable development, especially in terms of deep learning strategies. However, these studies usually rely heavily on considerable fine annotated data, while point-wise 3D LiDAR datasets are extremely insufficient and expensive to label. The performance limitation caused by the lack of training data is called the data hungry effect. This survey aims to explore whether and how we are hungry for 3D LiDAR data for semantic segmentation. Thus, we first provide an organized review of existing 3D datasets and 3D semantic segmentation methods. Then, we provide an in-depth analysis of three representative datasets and several experiments to evaluate the data hungry effects in different aspects. Efforts to solve data hungry problems are summarized for both 3D LiDAR-focused methods and general-purpose methods. Finally, insightful topics are discussed for future research on data hungry problems and open questions.

* 26 pages, 18 figures 

  Access Paper or Ask Questions

Physical Human-Robot Interaction with a Tethered Aerial Vehicle: Application to a Force-based Human Guiding Problem

May 14, 2020
Marco Tognon, Rachid Alami, Bruno Siciliano

Today, physical Human-Robot Interaction (pHRI) is a very popular topic in the field of ground manipulation. At the same time, Aerial Physical Interaction (APhI) is also developing very fast. Nevertheless, pHRI with aerial vehicles has not been addressed so far. In this work, we present the study of one of the first systems in which a human is physically connected to an aerial vehicle by a cable. We want the robot to be able to pull the human toward a desired position (or along a path) only using forces as an indirect communication-channel. We propose an admittance-based approach that makes pHRI safe. A controller, inspired by the literature on flexible manipulators, computes the desired interaction forces that properly guide the human. The stability of the system is formally proved with a Lyapunov-based argument. The system is also shown to be passive, and thus robust to non-idealities like additional human forces, time-varying inputs, and other external disturbances. We also design a maneuver regulation policy to simplify the path following problem. The global method has been experimentally validated on a group of four subjects, showing a reliable and safe pHRI.

  Access Paper or Ask Questions

Federated Extra-Trees with Privacy Preserving

Feb 18, 2020
Yang Liu, Mingxin Chen, Wenxi Zhang, Junbo Zhang, Yu Zheng

It is commonly observed that the data are scattered everywhere and difficult to be centralized. The data privacy and security also become a sensitive topic. The laws and regulations such as the European Union's General Data Protection Regulation (GDPR) are designed to protect the public's data privacy. However, machine learning requires a large amount of data for better performance, and the current circumstances put deploying real-life AI applications in an extremely difficult situation. To tackle these challenges, in this paper we propose a novel privacy-preserving federated machine learning model, named Federated Extra-Trees, which applies local differential privacy in the federated trees model. A secure multi-institutional machine learning system was developed to provide superior performance by processing the modeling jointly on different clients without exchanging any raw data. We have validated the accuracy of our work by conducting extensive experiments on public datasets and the efficiency and robustness were also verified by simulating the real-world scenarios. Overall, we presented an extensible, scalable and practical solution to handle the data island problem.

  Access Paper or Ask Questions