Related papers: Lessons Learned Addressing Dataset Bias in Model-B…
Model selection is a central task in statistics, but standard methods are not robust in misspecified settings where the true data-generating process (DGP) is not in the set of candidate models. The key limitation is that existing methods --…
Synthetic data generation has been widely adopted in software testing, data privacy, imbalanced learning, and artificial intelligence explanation. In all such contexts, it is crucial to generate plausible data samples. A common assumption…
Twitter is a popular microblogging platform. When users send out messages, other users have the ability to forward these messages to their own subgraph. Most research focuses on increasing retweetability from a node's perspective. Here, we…
Recent improvements in conditional generative modeling have made it possible to generate high-quality images from language descriptions alone. We investigate whether these methods can directly address the problem of sequential…
Providing users with alternatives to choose from is an essential component in many online platforms, making the accurate prediction of choice vital to their success. A renewed interest in learning choice models has led to significant…
As machine learning methods are deployed in real-world settings such as healthcare, legal systems, and social science, it is crucial to recognize how they shape social biases and stereotypes in these sensitive decision-making processes.…
We introduce and motivate generative modeling as a central task for machine learning and provide a critical view of the algorithms which have been proposed for solving this task. We overview how generative modeling can be defined…
Large pre-trained language models (LMs) have been shown to perform surprisingly well when fine-tuned on tasks that require commonsense and world knowledge. However, in end-to-end architectures, it is difficult to explain what is the…
Model explainability is crucial for human users to be able to interpret how a proposed classifier assigns labels to data based on its feature values. We study generalized linear models constructed using sets of feature value rules, which…
Decision making in crucial applications such as lending, hiring, and college admissions has witnessed increasing use of algorithmic models and techniques as a result of a confluence of factors such as ubiquitous connectivity, ability to…
The underlying paradigm of big data-driven machine learning reflects the desire of deriving better conclusions from simply analyzing more data, without the necessity of looking at theory and models. Is having simply more data always…
Controllable text generation concerns two fundamental tasks of wide applications, namely generating text of given attributes (i.e., attribute-conditional generation), and minimally editing existing text to possess desired attributes (i.e.,…
Thanks to the recent development of deep generative models, it is becoming possible to generate high-quality images with both fidelity and diversity. However, the training of such generative models requires a large dataset. To reduce the…
Harmful content detection models tend to have higher false positive rates for content from marginalized groups. In the context of marginal abuse modeling on Twitter, such disproportionate penalization poses the risk of reduced visibility,…
This work addresses fair generative models. Dataset biases have been a major cause of unfairness in deep generative models. Previous work had proposed to augment large, biased datasets with small, unbiased reference datasets. Under this…
With the rise in popularity of public social media and micro-blogging services, most notably Twitter, the people have found a venue to hear and be heard by their peers without an intermediary. As a consequence, and aided by the public…
We propose a novel approach for using unsupervised boosting to create an ensemble of generative models, where models are trained in sequence to correct earlier mistakes. Our meta-algorithmic framework can leverage any existing base learner…
When using machine learning for imbalanced binary classification problems, it is common to subsample the majority class to create a (more) balanced training dataset. This biases the model's predictions because the model learns from data…
The neural text generation suffers from the text degeneration issue such as repetition. Traditional stochastic sampling methods only focus on truncating the unreliable "tail" of the distribution, and do not address the "head" part, which we…
Information leakage is becoming a critical problem as various information becomes publicly available by mistake, and machine learning models train on that data to provide services. As a result, one's private information could easily be…