More Like this

1. Generative Modeling Helps Weak Supervision (and Vice Versa)

   Boecking, B; Roberts, N; Neiswanger, W; Ermon, S; Sala, F; Dubrawski, A (January 2023, International Conference on Learning Representations)

   Many promising applications of supervised machine learning face hurdles in the acquisition of labeled data in sufficient quantity and quality, creating an expensive bottleneck. To overcome such limitations, techniques that do not depend on ground truth labels have been studied, including weak supervision and generative modeling. While these techniques would seem to be usable in concert, improving one another, how to build an interface between them is not well-understood. In this work, we propose a model fusing programmatic weak supervision and generative adversarial networks and provide theoretical justification motivating this fusion. The proposed approach captures discrete latent variables in the data alongside the weak supervision derived label estimate. Alignment of the two allows for better modeling of sample-dependent accuracies of the weak supervision sources, improving the estimate of unobserved labels. It is the first approach to enable data augmentation through weakly supervised synthetic images and pseudolabels. Additionally, its learned latent variables can be inspected qualitatively. The model outperforms baseline weak supervision label models on a number of multiclass image classification datasets, improves the quality of generated images, and further improves end-model performance through data augmentation with synthetic samples. 

   more » « less
2. Domain-specific analysis of mobile app reviews using keyword-assisted topic models

   https://doi.org/10.1145/3510003.3510201  

   Tushev, M.; Ebrahimi, F.; Mahmoud, A. (May 2022, Proceedings of the International Conference on Software Engineering)

   Mobile application (app) reviews contain valuable information for app developers. A plethora of supervised and unsupervised techniques have been proposed in the literature to synthesize useful user feedback from app reviews. However, traditional supervised classification algorithms require extensive manual effort to label ground truth data, while unsupervised text mining techniques, such as topic models, often produce suboptimal results due to the sparsity of useful information in the reviews. To overcome these limitations, in this paper, we propose a fully automatic and unsupervised approach for extracting useful information from mobile app reviews. The proposed approach is based on keyATM, a keyword-assisted approach for generating topic models. keyATM overcomes the problem of data sparsity by using seeding keywords extracted directly from the review corpus. These keywords are then used to generate meaningful domain-specific topics. Our approach is evaluated over two datasets of mobile app reviews sampled from the domains of Investing and Food Delivery apps. The results show that our approach produces significantly more coherent topics than traditional topic modeling techniques. 

   more » « less
3. A Joint Learning Approach for Semi-supervised Neural Topic Modeling

   https://doi.org/10.18653/v1/2022.spnlp-1.5  

   Chiu, Jeffrey; Mittal, Rajat; Tumma, Neehal; Sharma, Abhishek; Doshi-Velez, Finale (May 2022, Proceedings of the Sixth Workshop on Structured Prediction for NLP)

   Topic models are some of the most popular ways to represent textual data in an interpret- able manner. Recently, advances in deep gen- erative models, specifically auto-encoding vari- ational Bayes (AEVB), have led to the intro- duction of unsupervised neural topic models, which leverage deep generative models as op- posed to traditional statistics-based topic mod- els. We extend upon these neural topic models by introducing the Label-Indexed Neural Topic Model (LI-NTM), which is, to the extent of our knowledge, the first effective upstream semi- supervised neural topic model. We find that LI- NTM outperforms existing neural topic models in document reconstruction benchmarks, with the most notable results in low labeled data regimes and for data-sets with informative la- bels; furthermore, our jointly learned classi- fier outperforms baseline classifiers in ablation studies. 

   more » « less
4. Machine Learning with Differentially Private Labels: Mechanisms and Frameworks

   https://doi.org/10.56553/popets-2022-0112  

   Tang, Xinyu; Nasr, Milad; Mahloujifar, Saeed; Shejwalkar, Virat; Song, Liwei; Houmansadr, Amir; Mittal, Prateek (October 2022, Proceedings on Privacy Enhancing Technologies)

   Label differential privacy is a relaxation of differential privacy for machine learning scenarios where the labels are the only sensitive information that needs to be protected in the training data. For example, imagine a survey from a participant in a university class about their vaccination status. Some attributes of the students are publicly available but their vaccination status is sensitive information and must remain private. Now if we want to train a model that predicts whether a student has received vaccination using only their public information, we can use label-DP. Recent works on label-DP use different ways of adding noise to the labels in order to obtain label-DP models. In this work, we present novel techniques for training models with label-DP guarantees by leveraging unsupervised learning and semi-supervised learning, enabling us to inject less noise while obtaining the same privacy, therefore achieving a better utility-privacy trade-off. We first introduce a framework that starts with an unsupervised classifier f0 and dataset D with noisy label set Y , reduces the noise in Y using f0 , and then trains a new model f using the less noisy dataset. Our noise reduction strategy uses the model f0 to remove the noisy labels that are incorrect with high probability. Then we use semi-supervised learning to train a model using the remaining labels. We instantiate this framework with multiple ways of obtaining the noisy labels and also the base classifier. As an alternative way to reduce the noise, we explore the effect of using unsupervised learning: we only add noise to a majority voting step for associating the learned clusters with a cluster label (as opposed to adding noise to individual labels); the reduced sensitivity enables us to add less noise. Our experiments show that these techniques can significantly outperform the prior works on label-DP. 

   more » « less
5. Weakly Supervised Spatial Deep Learning for Earth Image Segmentation Based on Imperfect Polyline Labels

   https://doi.org/10.1145/3480970  

   Jiang, Zhe; He, Wenchong; Kirby, Marcus Stephen; Sainju, Arpan Man; Wang, Shaowen; Stanislawski, Lawrence V.; Shavers, Ethan J.; Usery, E. Lynn (April 2022, ACM Transactions on Intelligent Systems and Technology)

   In recent years, deep learning has achieved tremendous success in image segmentation for computer vision applications. The performance of these models heavily relies on the availability of large-scale high-quality training labels (e.g., PASCAL VOC 2012). Unfortunately, such large-scale high-quality training data are often unavailable in many real-world spatial or spatiotemporal problems in earth science and remote sensing (e.g., mapping the nationwide river streams for water resource management). Although extensive efforts have been made to reduce the reliance on labeled data (e.g., semi-supervised or unsupervised learning, few-shot learning), the complex nature of geographic data such as spatial heterogeneity still requires sufficient training labels when transferring a pre-trained model from one region to another. On the other hand, it is often much easier to collect lower-quality training labels with imperfect alignment with earth imagery pixels (e.g., through interpreting coarse imagery by non-expert volunteers). However, directly training a deep neural network on imperfect labels with geometric annotation errors could significantly impact model performance. Existing research that overcomes imperfect training labels either focuses on errors in label class semantics or characterizes label location errors at the pixel level. These methods do not fully incorporate the geometric properties of label location errors in the vector representation. To fill the gap, this article proposes a weakly supervised learning framework to simultaneously update deep learning model parameters and infer hidden true vector label locations. Specifically, we model label location errors in the vector representation to partially reserve geometric properties (e.g., spatial contiguity within line segments). Evaluations on real-world datasets in the National Hydrography Dataset (NHD) refinement application illustrate that the proposed framework outperforms baseline methods in classification accuracy. 

   more » « less