To address the sample selection bias between the training and test
data, previous research works focus on reweighing biased training
data to match the test data and then building classification models
on there weighed raining data. However, how to achieve fairness
in the built classification models is under-explored. In this paper,
we propose a framework for robust and fair learning under sample
selection bias. Our framework adopts there weighing estimation
approach for bias correction and the minimax robust estimation approach for achieving robustness on prediction accuracy. Moreover,
during the minimax optimization, the fairness is achieved under
the worst case, which guarantees the model’s fairness on test data.
We further develop two algorithms to handle sample selection bias
when test data is both available and unavailable.
more »
« less
Test-Time Training with Self-Supervision for Generalization under Distribution Shifts
In this paper, we propose Test-Time Training, a general approach for improving the performance of predictive models when training and test data come from different distributions. We turn a single unlabeled test sample into a self-supervised learning problem, on which we update the model parameters before making a prediction. This also extends naturally to data in an online stream. Our simple approach leads to improvements on diverse image classification benchmarks aimed at evaluating robustness to distribution shifts.
more »
« less
- Award ID(s):
- 1764033
- PAR ID:
- 10249254
- Date Published:
- Journal Name:
- ICML 2020
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Over the past few years, Large Language Models of Code (Code LLMs) have started to have a significant impact on programming practice. Code LLMs are also emerging as building blocks for research in programming languages and software engineering. However, the quality of code produced by a Code LLM varies significantly by programming language. Code LLMs produce impressive results on high-resource programming languages that are well represented in their training data (e.g., Java, Python, or JavaScript), but struggle with low-resource languages that have limited training data available (e.g., OCaml, Racket, and several others). This paper presents an effective approach for boosting the performance of Code LLMs on low-resource languages using semi-synthetic data. Our approach, called MultiPL-T, generates high-quality datasets for low-resource languages, which can then be used to fine-tune any pretrained Code LLM. MultiPL-T translates training data from high-resource languages into training data for low-resource languages in the following way. 1) We use a Code LLM to synthesize unit tests for commented code from a high-resource source language, filtering out faulty tests and code with low test coverage. 2) We use a Code LLM to translate the code from the high-resource source language to a target low-resource language. This gives us a corpus of candidate training data in the target language, but many of these translations are wrong. 3) We use a lightweight compiler to compile the test cases generated in (1) from the source language to the target language, which allows us to filter our obviously wrong translations. The result is a training corpus in the target low-resource language where all items have been validated with test cases. We apply this approach to generate tens of thousands of new, validated training items for five low-resource languages: Julia, Lua, OCaml, R, and Racket, using Python as the source high-resource language. Furthermore, we use an open Code LLM (StarCoderBase) with open training data (The Stack), which allows us to decontaminate benchmarks, train models without violating licenses, and run experiments that could not otherwise be done. Using datasets generated with MultiPL-T, we present fine-tuned versions of StarCoderBase and Code Llama for Julia, Lua, OCaml, R, and Racket that outperform other fine-tunes of these base models on the natural language to code task. We also present Racket fine-tunes for two very recent models, DeepSeek Coder and StarCoder2, to show that MultiPL-T continues to outperform other fine-tuning approaches for low-resource languages. The MultiPL-T approach is easy to apply to new languages, and is significantly more efficient and effective than alternatives such as training longer.more » « less
-
null (Ed.)In this work, we consider learning a wafer plot recognizer where only one training sample is available. We introduce an approach called Manifestation Learning to enable the learning. The underlying technology utilizes the Variational AutoEncoder (VAE) approach to construct a so-called Manifestation Space. The training sample is projected into this space and the recognition is achieved through a pre-trained model in the space. Using wafer probe test data from an automotive product line, this paper explains the learning approach, its feasibility and limitation.more » « less
-
n this paper, we use a thermal camera to distinguish hard and soft swipes performed by a user interacting with a natural surface by detecting differences in the thermal signature of the surface due to heat transferred by the user. Unlike prior work, our approach provides swipe pressure classifiers that are user-agnostic, i.e., that recognize the swipe pressure of a novel user not present in the training set, enabling our work to be ported into natural user interfaces without user-specific calibration. Our approach generates average classification accuracy of 76% using random forest classifiers trained on a test set of 9 subjects interacting with paper and wood, with 8 hard and 8 soft test swipes per user. We compare results of the user-agnostic classification to user-aware classification with classifiers trained by including training samples from the user. We obtain average user-aware classification accuracy of 82% by adding up to 8 hard and 8 soft training swipes for each test user. Our approach enables seamless adaptation of generic pressure classification systems based on thermal data to the specific behavior of users interacting with natural user interfaces.more » « less
-
null (Ed.)Due to the extreme scarcity of customer failure data, it is challenging to reliably screen out those rare defects within a high-dimensional input feature space formed by the relevant parametric test measurements. In this paper, we study several unsupervised learning techniques based on six industrial test datasets, and propose to train a more robust unsupervised learning model by self-labeling the training data via a set of transformations. Using the labeled data we train a multi-class classifier through supervised training. The goodness of the multi-class classification decisions with respect to an unseen input data is used as a normality score to defect anomalies. Furthermore, we propose to use reversible information lossless transformations to retain the data information and boost the performance and robustness of the proposed self-labeling approach.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
