Non-I.I.D. Multi-Instance Learning for Predicting Instance and Bag Labels with Variational Auto-Encoder

Variational Autoencoder ◽

Label Prediction ◽

Weakly Supervised ◽

Better Than

Multi-instance learning is a type of weakly supervised learning. It deals with tasks where the data is a set of bags and each bag is a set of instances. Only the bag labels are observed whereas the labels for the instances are unknown. An important advantage of multi-instance learning is that by representing objects as a bag of instances, it is able to preserve the inherent dependencies among parts of the objects. Unfortunately, most existing algorithms assume all instances to be identically and independently distributed, which violates real-world scenarios since the instances within a bag are rarely independent. In this work, we propose the Multi-Instance Variational Autoencoder (MIVAE) algorithm which explicitly models the dependencies among the instances for predicting both bag labels and instance labels. Experimental results on several multi-instance benchmarks and end-to-end medical imaging datasets demonstrate that MIVAE performs better than state-of-the-art algorithms for both instance label and bag label prediction tasks.

Weakly Supervised Disentanglement by Pairwise Similarities

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v34i04.5754 ◽

2020 ◽

Vol 34 (04) ◽

pp. 3495-3502 ◽

Cited By ~ 1

Author(s):

Junxiang Chen ◽

Kayhan Batmanghelich

Keyword(s):

Real World ◽

Latent Variables ◽

Generative Models ◽

Experimental Results ◽

New Method ◽

Weak Supervision ◽

Real World Problem ◽

Variational Autoencoder ◽

Recently, researches related to unsupervised disentanglement learning with deep generative models have gained substantial popularity. However, without introducing supervision, there is no guarantee that the factors of interest can be successfully recovered (Locatello et al. 2018). Motivated by a real-world problem, we propose a setting where the user introduces weak supervision by providing similarities between instances based on a factor to be disentangled. The similarity is provided as either a binary (yes/no) or real-valued label describing whether a pair of instances are similar or not. We propose a new method for weakly supervised disentanglement of latent variables within the framework of Variational Autoencoder. Experimental results demonstrate that utilizing weak supervision improves the performance of the disentanglement method substantially.

Weakly supervised learning of information structure of scientific abstracts--is it accurate enough to benefit real-world tasks in biomedicine?

Bioinformatics ◽

10.1093/bioinformatics/btr536 ◽

2011 ◽

Vol 27 (22) ◽

pp. 3179-3185 ◽

Cited By ~ 8

Author(s):

Y. Guo ◽

A. Korhonen ◽

I. Silins ◽

U. Stenius

Keyword(s):

Supervised Learning ◽

Real World ◽

Information Structure ◽

Real-World Anomaly Detection by using Digital Twin Systems and Weakly-Supervised Learning

IEEE Transactions on Industrial Informatics ◽

10.1109/tii.2020.3019788 ◽

2020 ◽

pp. 1-1

Author(s):

Andrea Castellani ◽

Sebastian Schmitt ◽

Stefano Squartini

Keyword(s):

Anomaly Detection ◽

Supervised Learning ◽

Real World ◽

Digital Twin ◽

Cross-lingual Projected Expectation Regularization for Weakly Supervised Learning

Transactions of the Association for Computational Linguistics ◽

10.1162/tacl_a_00165 ◽

2014 ◽

Vol 2 ◽

pp. 55-66 ◽

Cited By ~ 10

Author(s):

Mengqiu Wang ◽

Christopher D. Manning

Keyword(s):

Supervised Learning ◽

Model Uncertainty ◽

State Of The Art ◽

New Method ◽

Supervised Methods ◽

Weakly Supervised ◽

Language Boundaries ◽

Standard Chinese ◽

Cross Lingual

We consider a multilingual weakly supervised learning scenario where knowledge from annotated corpora in a resource-rich language is transferred via bitext to guide the learning in other languages. Past approaches project labels across bitext and use them as features or gold labels for training. We propose a new method that projects model expectations rather than labels, which facilities transfer of model uncertainty across language boundaries. We encode expectations as constraints and train a discriminative CRF model using Generalized Expectation Criteria (Mann and McCallum, 2010). Evaluated on standard Chinese-English and German-English NER datasets, our method demonstrates F1 scores of 64% and 60% when no labeled data is used. Attaining the same accuracy with supervised CRFs requires 12k and 1.5k labeled sentences. Furthermore, when combined with labeled examples, our method yields significant improvements over state-of-the-art supervised methods, achieving best reported numbers to date on Chinese OntoNotes and German CoNLL-03 datasets.

Explicit Document Modeling through Weighted Multiple-Instance Learning

Journal of Artificial Intelligence Research ◽

10.1613/jair.5240 ◽

2017 ◽

Vol 58 ◽

pp. 591-626 ◽

Cited By ~ 8

Author(s):

Nikolaos Pappas ◽

Andrei Popescu-Belis

Keyword(s):

Sentiment Analysis ◽

Supervised Learning ◽

State Of The Art ◽

Multiple Instance Learning ◽

Fixed Length ◽

Document Modeling ◽

Crucial Component ◽

Document Vector ◽

Representing documents is a crucial component in many NLP tasks, for instance predicting aspect ratings in reviews. Previous methods for this task treat documents globally, and do not acknowledge that target categories are often assigned by their authors with generally no indication of the specific sentences that motivate them. To address this issue, we adopt a weakly supervised learning model, which jointly learns to focus on relevant parts of a document according to the context along with a classifier for the target categories. Derived from the weighted multiple-instance regression (MIR) framework, the model learns decomposable document vectors for each individual category and thus overcomes the representational bottleneck in previous methods due to a fixed-length document vector. During prediction, the estimated relevance or saliency weights explicitly capture the contribution of each sentence to the predicted rating, thus offering an explanation of the rating. Our model achieves state-of-the-art performance on multi-aspect sentiment analysis, improving over several baselines. Moreover, the predicted saliency weights are close to human estimates obtained by crowdsourcing, and increase the performance of lexical and topical features for review segmentation and summarization.