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

A Distributed Fair Machine Learning Framework with Private Demographic Data Protection

Sep 17, 2019
Hui Hu, Yijun Liu, Zhen Wang, Chao Lan

Fair machine learning has become a significant research topic with broad societal impact. However, most fair learning methods require direct access to personal demographic data, which is increasingly restricted to use for protecting user privacy (e.g. by the EU General Data Protection Regulation). In this paper, we propose a distributed fair learning framework for protecting the privacy of demographic data. We assume this data is privately held by a third party, which can communicate with the data center (responsible for model development) without revealing the demographic information. We propose a principled approach to design fair learning methods under this framework, exemplify four methods and show they consistently outperform their existing counterparts in both fairness and accuracy across three real-world data sets. We theoretically analyze the framework, and prove it can learn models with high fairness or high accuracy, with their trade-offs balanced by a threshold variable.

* 9 pages,4 figures,International Conference of Data Mining 

  Access Paper or Ask Questions

Cross-Enhancement Transform Two-Stream 3D ConvNets for Pedestrian Action Recognition of Autonomous Vehicles

Aug 19, 2019
Dong Cao, Lisha Xu

Action recognition is an important research topic in machine vision. It is widely used in many fields and is one of the key technologies in pedestrian behavior recognition and intention prediction in the field of autonomous driving. Based on the widely used 3D ConvNets algorithm, combined with Two-Stream Inflated algorithm and transfer learning algorithm, we construct a Cross-Enhancement Transform based Two-Stream 3D ConvNets algorithm. On the datasets with different data distribution characteristics, the performance of the algorithm is different, especially the performance of the RGB and optical flow stream in the two stream is different. For this case, we combine the data distribution characteristics on the specific dataset. As a teaching model, the stream with better performance in the two stream is used to assist in training another stream, and then two stream inference is made. We conducted experiments on the UCF-101, HMDB-51, and Kinetics data sets, and the experimental results confirmed the effectiveness of our algorithm.

* Accepted for publication in AIIPCC 2019 

  Access Paper or Ask Questions

Learning while Competing -- 3D Modeling & Design

May 18, 2019
Kalind Karia, Rucmenya Bessariya, Krishna Lala, Kavi Arya

The e-Yantra project at IIT Bombay conducts an online competition, e-Yantra Robotics Competition (eYRC) which uses a Project Based Learning (PBL) methodology to train students to implement a robotics project in a step-by-step manner over a five-month period. Participation is absolutely free. The competition provides all resources - robot, accessories, and a problem statement - to a participating team. If selected for the finals, e-Yantra pays for them to come to the finals at IIT Bombay. This makes the competition accessible to resource-poor student teams. In this paper, we describe the methodology used in the 6th edition of eYRC, eYRC-2017 where we experimented with a Theme (projects abstracted into rulebooks) involving an advanced topic - 3D Designing and interfacing with sensors and actuators. We demonstrate that the learning outcomes are consistent with our previous studies [1]. We infer that even 3D designing to create a working model can be effectively learned in a competition mode through PBL.


  Access Paper or Ask Questions

Applications of Social Media in Hydroinformatics: A Survey

May 01, 2019
Yufeng Yu, Yuelong Zhu, Dingsheng Wan, Qun Zhao, Kai Shu, Huan Liu

Floods of research and practical applications employ social media data for a wide range of public applications, including environmental monitoring, water resource managing, disaster and emergency response.Hydroinformatics can benefit from the social media technologies with newly emerged data, techniques and analytical tools to handle large datasets, from which creative ideas and new values could be mined.This paper first proposes a 4W (What, Why, When, hoW) model and a methodological structure to better understand and represent the application of social media to hydroinformatics, then provides an overview of academic research of applying social media to hydroinformatics such as water environment, water resources, flood, drought and water Scarcity management. At last,some advanced topics and suggestions of water related social media applications from data collection, data quality management, fake news detection, privacy issues, algorithms and platforms was present to hydroinformatics managers and researchers based on previous discussion.

* 37pages 

  Access Paper or Ask Questions

Deep Learning to Predict Student Outcomes

Apr 27, 2019
Byung-Hak Kim

The increasingly fast development cycle for online course contents, along with the diverse student demographics in each online classroom, make real-time student outcomes prediction an interesting topic for both industrial research and practical needs. In this paper, we tackle the problem of real-time student performance prediction in an on-going course using a domain adaptation framework. This framework is a system trained on labeled student outcome data from previous coursework but is meant to be deployed on another course. In particular, we introduce a GritNet architecture, and develop an unsupervised domain adaptation method to transfer a GritNet trained on a past course to a new course without any student outcome label. Our results for real Udacity student graduation predictions show that the GritNet not only generalizes well from one course to another across different Nanodegree programs, but also enhances real-time predictions explicitly in the first few weeks when accurate predictions are most challenging.

* Accepted as oral presentation to ICLR 2019, AI for Social Good Workshop. arXiv admin note: substantial text overlap with arXiv:1809.06686, arXiv:1804.07405 

  Access Paper or Ask Questions

Condition-Transforming Variational AutoEncoder for Conversation Response Generation

Apr 24, 2019
Yu-Ping Ruan, Zhen-Hua Ling, Quan Liu, Zhigang Chen, Nitin Indurkhya

This paper proposes a new model, called condition-transforming variational autoencoder (CTVAE), to improve the performance of conversation response generation using conditional variational autoencoders (CVAEs). In conventional CVAEs , the prior distribution of latent variable z follows a multivariate Gaussian distribution with mean and variance modulated by the input conditions. Previous work found that this distribution tends to become condition independent in practical application. In our proposed CTVAE model, the latent variable z is sampled by performing a non-lineartransformation on the combination of the input conditions and the samples from a condition-independent prior distribution N (0; I). In our objective evaluations, the CTVAE model outperforms the CVAE model on fluency metrics and surpasses a sequence-to-sequence (Seq2Seq) model on diversity metrics. In subjective preference tests, our proposed CTVAE model performs significantly better than CVAE and Seq2Seq models on generating fluency, informative and topic relevant responses.

* ICASSP 2019, oral 

  Access Paper or Ask Questions

Persistence Curves: A canonical framework for summarizing persistence diagrams

Apr 16, 2019
Yu-Min Chung, Austin Lawson

Persistence diagrams are a main tool in the field of Topological Data Analysis (TDA). They contain fruitful information about the shape of data. The use of machine learning algorithms on the space of persistence diagrams proves to be challenging as the space is complicated. For that reason, summarizing and vectorizing these diagrams is an important topic currently researched in TDA. In this work, we provide a general framework of summarizing diagrams that we call Persistence Curves (PC). The main idea is so-called Fundamental Lemma of Persistent Homology, which is derived from the classic elder rule. Under this framework, certain well-known summaries, such as persistent Betti numbers, and persistence landscape, are special cases of the PC. Moreover, we prove a rigorous bound for a general families of PCs. In particular, certain family of PCs admit the stability property under an additional assumption. Finally, we apply PCs to textures classification on four well-know texture datasets. The result outperforms several existing TDA methods.


  Access Paper or Ask Questions

Evaluating Coherence in Dialogue Systems using Entailment

Apr 06, 2019
Nouha Dziri, Ehsan Kamalloo, Kory W. Mathewson, Osmar Zaiane

Evaluating open-domain dialogue systems is difficult due to the diversity of possible correct answers. Automatic metrics such as BLEU correlate weakly with human annotations, resulting in a significant bias across different models and datasets. Some researchers resort to human judgment experimentation for assessing response quality, which is expensive, time consuming, and not scalable. Moreover, judges tend to evaluate a small number of dialogues, meaning that minor differences in evaluation configuration may lead to dissimilar results. In this paper, we present interpretable metrics for evaluating topic coherence by making use of distributed sentence representations. Furthermore, we introduce calculable approximations of human judgment based on conversational coherence by adopting state-of-the-art entailment techniques. Results show that our metrics can be used as a surrogate for human judgment, making it easy to evaluate dialogue systems on large-scale datasets and allowing an unbiased estimate for the quality of the responses.

* 5 pages, 2 figures; NAACL-HLT 2019 

  Access Paper or Ask Questions

Short-term forecasting of Italian gas demand

Jan 31, 2019
Emanuele Fabbiani, Andrea Marziali, Giuseppe De Nicolao

Forecasting natural gas demand is a key problem for energy providers, as it allows for efficient pipe reservation and power plant allocation, and enables effective price forecasting. We propose a study of Italian gas demand, with particular focus on industrial and thermoelectric components. To the best of our knowledge, this is the first work about these topics. After a preliminary discussion on the characteristics of gas demand, we apply several statistical learning models to perform day-ahead forecasting, including regularized linear models, random forest, support vector regression and neural networks. Moreover, we introduce four simple ensemble models and we compare their performance with the one of basic forecasters. The out-of-sample Mean Absolute Error (MAE) achieved on 2017 by our best ensemble model is 5.16 Millions of Standard Cubic Meters (MSCM), lower than 9.57 MSCM obtained by the predictions issued by SNAM, the Italian Transmission System Operator (TSO).


  Access Paper or Ask Questions

Generalised Differential Privacy for Text Document Processing

Nov 26, 2018
Natasha Fernandes, Mark Dras, Annabelle McIver

We address the problem of how to "obfuscate" texts by removing stylistic clues which can identify authorship, whilst preserving (as much as possible) the content of the text. In this paper we combine ideas from "generalised differential privacy" and machine learning techniques for text processing to model privacy for text documents. We define a privacy mechanism that operates at the level of text documents represented as "bags-of-words" - these representations are typical in machine learning and contain sufficient information to carry out many kinds of classification tasks including topic identification and authorship attribution (of the original documents). We show that our mechanism satisfies privacy with respect to a metric for semantic similarity, thereby providing a balance between utility, defined by the semantic content of texts, with the obfuscation of stylistic clues. We demonstrate our implementation on a "fan fiction" dataset, confirming that it is indeed possible to disguise writing style effectively whilst preserving enough information and variation for accurate content classification tasks.


  Access Paper or Ask Questions

<<
335
336
337
338
339
340
341
342
343
344
345
346
347
>>