Tight Lower Bounds on Worst-Case Guarantees for Zero-Shot Learning with Attributes

We develop a rigorous mathematical analysis of zero-shot learning with attributes. In this setting, the goal is to label novel classes with no training data, only detectors for attributes and a description of how those attributes are correlated with the target classes, called the class-attribute matrix. We develop the first non-trivial lower bound on the worst-case error of the best map from attributes to classes for this setting, even with perfect attribute detectors. The lower bound characterizes the theoretical intrinsic difficulty of the zero-shot problem based on the available information -- the class-attribute matrix -- and the bound is practically computable from it. Our lower bound is tight, as we show that we can always find a randomized map from attributes to classes whose expected error is upper bounded by the value of the lower bound. We show that our analysis can be predictive of how standard zero-shot methods behave in practice, including which classes will likely be confused with others.

Fairness via Explanation Quality: Evaluating Disparities in the Quality of Post hoc Explanations

As post hoc explanation methods are increasingly being leveraged to explain complex models in high-stakes settings, it becomes critical to ensure that the quality of the resulting explanations is consistently high across various population subgroups including the minority groups. For instance, it should not be the case that explanations associated with instances belonging to a particular gender subgroup (e.g., female) are less accurate than those associated with other genders. However, there is little to no research that assesses if there exist such group-based disparities in the quality of the explanations output by state-of-the-art explanation methods. In this work, we address the aforementioned gaps by initiating the study of identifying group-based disparities in explanation quality. To this end, we first outline the key properties which constitute explanation quality and where disparities can be particularly problematic. We then leverage these properties to propose a novel evaluation framework which can quantitatively measure disparities in the quality of explanations output by state-of-the-art methods. Using this framework, we carry out a rigorous empirical analysis to understand if and when group-based disparities in explanation quality arise. Our results indicate that such disparities are more likely to occur when the models being explained are complex and highly non-linear. In addition, we also observe that certain post hoc explanation methods (e.g., Integrated Gradients, SHAP) are more likely to exhibit the aforementioned disparities. To the best of our knowledge, this work is the first to highlight and study the problem of group-based disparities in explanation quality. In doing so, our work sheds light on previously unexplored ways in which explanation methods may introduce unfairness in real world decision making.

Language Models in the Loop: Incorporating Prompting into Weak Supervision

We propose a new strategy for applying large pre-trained language models to novel tasks when labeled training data is limited. Rather than apply the model in a typical zero-shot or few-shot fashion, we treat the model as the basis for labeling functions in a weak supervision framework. To create a classifier, we first prompt the model to answer multiple distinct queries about an example and define how the possible responses should be mapped to votes for labels and abstentions. We then denoise these noisy label sources using the Snorkel system and train an end classifier with the resulting training data. Our experimental evaluation shows that prompting large language models within a weak supervision framework can provide significant gains in accuracy. On the WRENCH weak supervision benchmark, this approach can significantly improve over zero-shot performance, an average 19.5% reduction in errors. We also find that this approach produces classifiers with comparable or superior accuracy to those trained from hand-engineered rules.

Learning to Compose Soft Prompts for Compositional Zero-Shot Learning

We introduce compositional soft prompting (CSP), a parameter-efficient learning technique to improve the zero-shot compositionality of large-scale pretrained vision-language models (VLMs) without the overhead of fine-tuning the entire model. VLMs can represent arbitrary classes as natural language prompts in their flexible text encoders but they underperform state-of-the-art methods on compositional zero-shot benchmark tasks. To improve VLMs, we propose a novel form of soft prompting. We treat the attributes and objects that are composed to define classes as learnable tokens of vocabulary and tune them on multiple prompt compositions. During inference, we recompose the learned attribute-object vocabulary in new combinations and show that CSP outperforms the original VLM on benchmark datasets by an average of 14.7 percentage points of accuracy. CSP also achieves new state-of-the-art accuracies on two out of three benchmark datasets, while only fine-tuning a small number of parameters. Further, we show that CSP improves generalization to higher-order attribute-attribute-object compositions and combinations of pretrained attributes and fine-tuned objects.

PromptSource: An Integrated Development Environment and Repository for Natural Language Prompts

PromptSource is a system for creating, sharing, and using natural language prompts. Prompts are functions that map an example from a dataset to a natural language input and target output. Using prompts to train and query language models is an emerging area in NLP that requires new tools that let users develop and refine these prompts collaboratively. PromptSource addresses the emergent challenges in this new setting with (1) a templating language for defining data-linked prompts, (2) an interface that lets users quickly iterate on prompt development by observing outputs of their prompts on many examples, and (3) a community-driven set of guidelines for contributing new prompts to a common pool. Over 2,000 prompts for roughly 170 datasets are already available in PromptSource. PromptSource is available at https://github.com/bigscience-workshop/promptsource.

TAGLETS: A System for Automatic Semi-Supervised Learning with Auxiliary Data

Machine learning practitioners often have access to a spectrum of data: labeled data for the target task (which is often limited), unlabeled data, and auxiliary data, the many available labeled datasets for other tasks. We describe TAGLETS, a system built to study techniques for automatically exploiting all three types of data and creating high-quality, servable classifiers. The key components of TAGLETS are: (1) auxiliary data organized according to a knowledge graph, (2) modules encapsulating different methods for exploiting auxiliary and unlabeled data, and (3) a distillation stage in which the ensembled modules are combined into a servable model. We compare TAGLETS with state-of-the-art transfer learning and semi-supervised learning methods on four image classification tasks. Our study covers a range of settings, varying the amount of labeled data and the semantic relatedness of the auxiliary data to the target task. We find that the intelligent incorporation of auxiliary and unlabeled data into multiple learning techniques enables TAGLETS to match-and most often significantly surpass-these alternatives. TAGLETS is available as an open-source system at github.com/BatsResearch/taglets.

Multitask Prompted Training Enables Zero-Shot Task Generalization

Large language models have recently been shown to attain reasonable zero-shot generalization on a diverse set of tasks. It has been hypothesized that this is a consequence of implicit multitask learning in language model training. Can zero-shot generalization instead be directly induced by explicit multitask learning? To test this question at scale, we develop a system for easily mapping general natural language tasks into a human-readable prompted form. We convert a large set of supervised datasets, each with multiple prompts using varying natural language. These prompted datasets allow for benchmarking the ability of a model to perform completely unseen tasks specified in natural language. We fine-tune a pretrained encoder-decoder model on this multitask mixture covering a wide variety of tasks. The model attains strong zero-shot performance on several standard datasets, often outperforming models 16x its size. Further, our approach attains strong performance on a subset of tasks from the BIG-Bench benchmark, outperforming models 6x its size. All prompts and trained models are available at github.com/bigscience-workshop/promptsource/.

What will it take to generate fairness-preserving explanations?

In situations where explanations of black-box models may be useful, the fairness of the black-box is also often a relevant concern. However, the link between the fairness of the black-box model and the behavior of explanations for the black-box is unclear. We focus on explanations applied to tabular datasets, suggesting that explanations do not necessarily preserve the fairness properties of the black-box algorithm. In other words, explanation algorithms can ignore or obscure critical relevant properties, creating incorrect or misleading explanations. More broadly, we propose future research directions for evaluating and generating explanations such that they are informative and relevant from a fairness perspective.

Learning from Multiple Noisy Partial Labelers

Programmatic weak supervision creates models without hand-labeled training data by combining the outputs of noisy, user-written rules and other heuristic labelers. Existing frameworks make the restrictive assumption that labelers output a single class label. Enabling users to create partial labelers that output subsets of possible class labels would greatly expand the expressivity of programmatic weak supervision. We introduce this capability by defining a probabilistic generative model that can estimate the underlying accuracies of multiple noisy partial labelers without ground truth labels. We prove that this class of models is generically identifiable up to label swapping under mild conditions. We also show how to scale up learning to 100k examples in one minute, a 300X speed up compared to a naive implementation. We evaluate our framework on three text classification and six object classification tasks. On text tasks, adding partial labels increases average accuracy by 9.6 percentage points. On image tasks, we show that partial labels allow us to approach some zero-shot object classification problems with programmatic weak supervision by using class attributes as partial labelers. Our framework is able to achieve accuracy comparable to recent embedding-based zero-shot learning methods using only pre-trained attribute detectors

Pseudo Shots: Few-Shot Learning with Auxiliary Data

In many practical few-shot learning problems, even though labeled examples are scarce, there are abundant auxiliary data sets that potentially contain useful information. We propose a framework to address the challenges of efficiently selecting and effectively using auxiliary data in image classification. Given an auxiliary dataset and a notion of semantic similarity among classes, we automatically select pseudo shots, which are labeled examples from other classes related to the target task. We show that naively assuming that these additional examples come from the same distribution as the target task examples does not significantly improve accuracy. Instead, we propose a masking module that adjusts the features of auxiliary data to be more similar to those of the target classes. We show that this masking module can improve accuracy by up to 18 accuracy points, particularly when the auxiliary data is semantically distant from the target task. We also show that incorporating pseudo shots improves over the current state-of-the-art few-shot image classification scores by an average of 4.81 percentage points of accuracy on 1-shot tasks and an average of 0.31 percentage points on 5-shot tasks.