Search Results for author:
Found 85 papers, 45 papers with code
Toward Informal Language Processing: Knowledge of Slang in Large Language Models
Our work offers a comprehensive evaluation and a high-quality benchmark on English slang based on the OpenSubtitles corpus, serving both as a publicly accessible resource and a platform for applying tools for informal language processing.
Partial Federated Learning
Federated Learning (FL) is a popular algorithm to train machine learning models on user data constrained to edge devices (for example, mobile phones) due to privacy concerns.
Out of the Ordinary: Spectrally Adapting Regression for Covariate Shift
Designing deep neural network classifiers that perform robustly on distributions differing from the available training data is an active area of machine learning research.
Online Algorithmic Recourse by Collective Action
Research on algorithmic recourse typically considers how an individual can reasonably change an unfavorable automated decision when interacting with a fixed decision-making system.
Tokenization Matters: Navigating Data-Scarce Tokenization for Gender Inclusive Language Technologies
Our paper is the first to link LLM misgendering to tokenization and deficient neopronoun grammar, indicating that LLMs unable to correctly treat neopronouns as pronouns are more prone to misgender.
ICL Markup: Structuring In-Context Learning using Soft-Token Tags
Large pretrained language models (LLMs) can be rapidly adapted to a wide variety of tasks via a text-to-text approach, where the instruction and input are fed to the model in natural language.
Prompt Risk Control: A Rigorous Framework for Responsible Deployment of Large Language Models
The recent explosion in the capabilities of large language models has led to a wave of interest in how best to prompt a model to perform a given task.
JAB: Joint Adversarial Prompting and Belief Augmentation
With the recent surge of language models in different applications, attention to safety and robustness of these models has gained significant importance.
On the steerability of large language models toward data-driven personas
Large language models (LLMs) are known to generate biased responses where the opinions of certain groups and populations are underrepresented.
Coordinated Replay Sample Selection for Continual Federated Learning
Continual Federated Learning (CFL) combines Federated Learning (FL), the decentralized learning of a central model on a number of client devices that may not communicate their data, and Continual Learning (CL), the learning of a model from a continual stream of data without keeping the entire history.
Distribution-Free Statistical Dispersion Control for Societal Applications
Explicit finite-sample statistical guarantees on model performance are an important ingredient in responsible machine learning.
FLIRT: Feedback Loop In-context Red Teaming
Here we propose an automatic red teaming framework that evaluates a given model and exposes its vulnerabilities against unsafe and inappropriate content generation.
"I'm fully who I am": Towards Centering Transgender and Non-Binary Voices to Measure Biases in Open Language Generation
Transgender and non-binary (TGNB) individuals disproportionately experience discrimination and exclusion from daily life.
SURFSUP: Learning Fluid Simulation for Novel Surfaces
Modeling the mechanics of fluid in complex scenes is vital to applications in design, graphics, and robotics.
Quantile Risk Control: A Flexible Framework for Bounding the Probability of High-Loss Predictions
In this work, we propose a flexible framework to produce a family of bounds on quantiles of the loss distribution incurred by a predictor.
Is the Elephant Flying? Resolving Ambiguities in Text-to-Image Generative Models
Natural language often contains ambiguities that can lead to misinterpretation and miscommunication.
Differentially Private Decoding in Large Language Models
Recent large-scale natural language processing (NLP) systems use a pre-trained Large Language Model (LLM) on massive and diverse corpora as a headstart.
Semantically Informed Slang Interpretation
Slang is a predominant form of informal language making flexible and extended use of words that is notoriously hard for natural language processing systems to interpret.
Mapping the Multilingual Margins: Intersectional Biases of Sentiment Analysis Systems in English, Spanish, and Arabic
As natural language processing systems become more widespread, it is necessary to address fairness issues in their implementation and deployment to ensure that their negative impacts on society are understood and minimized.
Deep Ensembles Work, But Are They Necessary?
While deep ensembles are a practical way to achieve improvements to predictive power, uncertainty quantification, and robustness, our results show that these improvements can be replicated by a (larger) single model.
Variational Model Inversion Attacks
In this work, we provide a probabilistic interpretation of model inversion attacks, and formulate a variational objective that accounts for both diversity and accuracy.
Disentanglement and Generalization Under Correlation Shifts
Exploiting such correlations may increase predictive performance on noisy data; however, often correlations are not robust (e. g., they may change between domains, datasets, or applications) and models that exploit them do not generalize when correlations shift.
Identifying and Benchmarking Natural Out-of-Context Prediction Problems
Deep learning systems frequently fail at out-of-context (OOC) prediction, the problem of making reliable predictions on uncommon or unusual inputs or subgroups of the training distribution.
Online Unsupervised Learning of Visual Representations and Categories
Real world learning scenarios involve a nonstationary distribution of classes with sequential dependencies among the samples, in contrast to the standard machine learning formulation of drawing samples independently from a fixed, typically uniform distribution.
Directly Training Joint Energy-Based Models for Conditional Synthesis and Calibrated Prediction of Multi-Attribute Data
We find our models are capable of both accurate, calibrated predictions and high-quality conditional synthesis of novel attribute combinations.
NP-DRAW: A Non-Parametric Structured Latent Variable Model for Image Generation
1) We propose a non-parametric prior distribution over the appearance of image parts so that the latent variable ``what-to-draw'' per step becomes a categorical random variable.
Learning a Universal Template for Few-shot Dataset Generalization
Few-shot dataset generalization is a challenging variant of the well-studied few-shot classification problem where a diverse training set of several datasets is given, for the purpose of training an adaptable model that can then learn classes from new datasets using only a few examples.
Analyzing Monotonic Linear Interpolation in Neural Network Loss Landscapes
Linear interpolation between initial neural network parameters and converged parameters after training with stochastic gradient descent (SGD) typically leads to a monotonic decrease in the training objective.
A Computational Framework for Slang Generation
Slang is a common type of informal language, but its flexible nature and paucity of data resources present challenges for existing natural language systems.
Learning Flexible Classifiers with Shot-CONditional Episodic (SCONE) Training
We discover that fine-tuning on episodes of a particular shot can specialize the pre-trained model to solving episodes of that shot at the expense of performance on other shots, in agreement with a trade-off recently observed in the context of end-to-end episodic training.
Exploring representation learning for flexible few-shot tasks
In this work, we consider a realistic setting where the relationship between examples can change from episode to episode depending on the task context, which is not given to the learner.
A PAC-Bayesian Approach to Generalization Bounds for Graph Neural Networks
In this paper, we derive generalization bounds for the two primary classes of graph neural networks (GNNs), namely graph convolutional networks (GCNs) and message passing GNNs (MPGNNs), via a PAC-Bayesian approach.
Probing Few-Shot Generalization with Attributes
Despite impressive progress in deep learning, generalizing far beyond the training distribution is an important open challenge.
Fairness and Robustness in Invariant Learning: A Case Study in Toxicity Classification
Robustness is of central importance in machine learning and has given rise to the fields of domain generalization and invariant learning, which are concerned with improving performance on a test distribution distinct from but related to the training distribution.
Theoretical bounds on estimation error for meta-learning
Machine learning models have traditionally been developed under the assumption that the training and test distributions match exactly.
Environment Inference for Invariant Learning
Learning models that gracefully handle distribution shifts is central to research on domain generalization, robust optimization, and fairness.
Ranked #1 on
Out-of-Distribution Generalization
on ImageNet-W
Exchanging Lessons Between Algorithmic Fairness and Domain Generalization
Developing learning approaches that are not overly sensitive to the training distribution is central to research on domain- or out-of-distribution generalization, robust optimization and fairness.
Optimizing Long-term Social Welfare in Recommender Systems: A Constrained Matching Approach
We develop several scalable techniques to solve the matching problem, and also draw connections to various notions of user regret and fairness, arguing that these outcomes are fairer in a utilitarian sense.
Bayesian Few-Shot Classification with One-vs-Each Pólya-Gamma Augmented Gaussian Processes
Few-shot classification (FSC), the task of adapting a classifier to unseen classes given a small labeled dataset, is an important step on the path toward human-like machine learning.
Amortized Causal Discovery: Learning to Infer Causal Graphs from Time-Series Data
This enables us to train a single, amortized model that infers causal relations across samples with different underlying causal graphs, and thus leverages the shared dynamics information.
Shortcut Learning in Deep Neural Networks
Deep learning has triggered the current rise of artificial intelligence and is the workhorse of today's machine intelligence.
Learning the Stein Discrepancy for Training and Evaluating Energy-Based Models without Sampling
We estimate the Stein discrepancy between the data density $p(x)$ and the model density $q(x)$ defined by a vector function of the data.
SMILe: Scalable Meta Inverse Reinforcement Learning through Context-Conditional Policies
We examine the efficacy of our method on a variety of high-dimensional simulated continuous control tasks and observe that SMILe significantly outperforms Meta-BC.
A Divergence Minimization Perspective on Imitation Learning Methods
We present $f$-MAX, an $f$-divergence generalization of AIRL [Fu et al., 2018], a state-of-the-art IRL method.
Out-of-distribution Detection in Few-shot Classification
In this work, we propose tasks for out-of-distribution detection in the few-shot setting and establish benchmark datasets, based on four popular few-shot classification datasets.
Causal Modeling for Fairness in Dynamical Systems
In many application areas---lending, education, and online recommenders, for example---fairness and equity concerns emerge when a machine learning system interacts with a dynamically changing environment to produce both immediate and long-term effects for individuals and demographic groups.
Alchemy: A Quantum Chemistry Dataset for Benchmarking AI Models
We introduce a new molecular dataset, named Alchemy, for developing machine learning models useful in chemistry and material science.
Flexibly Fair Representation Learning by Disentanglement
We consider the problem of learning representations that achieve group and subgroup fairness with respect to multiple sensitive attributes.
Understanding the Limitations of Conditional Generative Models
Class-conditional generative models hold promise to overcome the shortcomings of their discriminative counterparts.
Understanding the Relation Between Maximum-Entropy Inverse Reinforcement Learning and Behaviour Cloning
$f$-MAX provides grounds for more directly comparing the objectives for LfD.
High-Level Perceptual Similarity is Enabled by Learning Diverse Tasks
Predicting human perceptual similarity is a challenging subject of ongoing research.
Learning Latent Subspaces in Variational Autoencoders
We consider the problem of unsupervised learning of features correlated to specific labels in a dataset.
Excessive Invariance Causes Adversarial Vulnerability
Despite their impressive performance, deep neural networks exhibit striking failures on out-of-distribution inputs.
Understanding the Origins of Bias in Word Embeddings
Given a word embedding trained on a corpus, our method identifies how perturbing the corpus will affect the bias of the resulting embedding.
Neural Guided Constraint Logic Programming for Program Synthesis
Synthesizing programs using example input/outputs is a classic problem in artificial intelligence.
Fairness Through Causal Awareness: Learning Latent-Variable Models for Biased Data
Building on prior work in deep learning and generative modeling, we describe how to learn the parameters of this causal model from observational data alone, even in the presence of unobserved confounders.
The Elephant in the Room
We showcase a family of common failures of state-of-the art object detectors.
Distilling the Posterior in Bayesian Neural Networks
We propose a framework, Adversarial Posterior Distillation, to distill the SGLD samples using a Generative Adversarial Network (GAN).
Adversarial Distillation of Bayesian Neural Network Posteriors
We propose a framework, Adversarial Posterior Distillation, to distill the SGLD samples using a Generative Adversarial Network (GAN).
Aggregated Momentum: Stability Through Passive Damping
Momentum is a simple and widely used trick which allows gradient-based optimizers to pick up speed along low curvature directions.
Inference in Probabilistic Graphical Models by Graph Neural Networks
Message-passing algorithms, such as belief propagation, are a natural way to disseminate evidence amongst correlated variables while exploiting the graph structure, but these algorithms can struggle when the conditional dependency graphs contain loops.
Reviving and Improving Recurrent Back-Propagation
We examine all RBP variants along with BPTT and TBPTT in three different application domains: associative memory with continuous Hopfield networks, document classification in citation networks using graph neural networks and hyperparameter optimization for fully connected networks.
Graph Partition Neural Networks for Semi-Supervised Classification
We present graph partition neural networks (GPNN), an extension of graph neural networks (GNNs) able to handle extremely large graphs.
Learning Adversarially Fair and Transferable Representations
In this paper, we advocate for representation learning as the key to mitigating unfair prediction outcomes downstream.
Neural Relational Inference for Interacting Systems
Interacting systems are prevalent in nature, from dynamical systems in physics to complex societal dynamics.
Predict Responsibly: Increasing Fairness by Learning to Defer
When machine learning models are used for high-stakes decisions, they should predict accurately, fairly, and responsibly.
Predict Responsibly: Improving Fairness and Accuracy by Learning to Defer
We propose a learning algorithm which accounts for potential biases held by external decision-makers in a system.
Few-Shot Learning Through an Information Retrieval Lens
Few-shot learning refers to understanding new concepts from only a few examples.
Dualing GANs
We start from linear discriminators in which case conjugate duality provides a mechanism to reformulate the saddle point objective into a maximization problem, such that both the generator and the discriminator of this 'dualing GAN' act in concert.
Causal Effect Inference with Deep Latent-Variable Models
Learning individual-level causal effects from observational data, such as inferring the most effective medication for a specific patient, is a problem of growing importance for policy makers.
Ranked #9 on
Causal Inference
on IHDP
Understanding the Effective Receptive Field in Deep Convolutional Neural Networks
We study characteristics of receptive fields of units in deep convolutional networks.
Learning Deep Parsimonious Representations
In this paper we aim at facilitating generalization for deep networks while supporting interpretability of the learned representations.
Gated Graph Sequence Neural Networks
Graph-structured data appears frequently in domains including chemistry, natural language semantics, social networks, and knowledge bases.
Ranked #1 on
Graph Classification
on IPC-grounded
The Variational Fair Autoencoder
We investigate the problem of learning representations that are invariant to certain nuisance or sensitive factors of variation in the data while retaining as much of the remaining information as possible.
Ranked #4 on
Sentiment Analysis
on Multi-Domain Sentiment Dataset
Siamese neural networks for one-shot image recognition
The process of learning good features for machine learning applications can be very computationally expensive and may prove difficult in cases where little data is available.
Ranked #1 on
One-Shot Learning
on MNIST
(using extra training data)
Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books
Books are a rich source of both fine-grained information, how a character, an object or a scene looks like, as well as high-level semantics, what someone is thinking, feeling and how these states evolve through a story.
Exploring Models and Data for Image Question Answering
A suite of baseline results on this new dataset are also presented.
Ranked #5 on
Video Question Answering
on SUTD-TrafficQA
Generative Moment Matching Networks
We consider the problem of learning deep generative models from data.
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
Inspired by recent work in machine translation and object detection, we introduce an attention based model that automatically learns to describe the content of images.
Learning unbiased features
Different forms of representation learning can be derived from alternative definitions of unwanted bias, e. g., bias to particular tasks, domains, or irrelevant underlying data dimensions.
Mean-Field Networks
The mean field algorithm is a widely used approximate inference algorithm for graphical models whose exact inference is intractable.
On the Representational Efficiency of Restricted Boltzmann Machines
This paper examines the question: What kinds of distributions can be efficiently represented by Restricted Boltzmann Machines (RBMs)?
A Determinantal Point Process Latent Variable Model for Inhibition in Neural Spiking Data
Point processes are popular models of neural spiking behavior as they provide a statistical distribution over temporal sequences of spikes and help to reveal the complexities underlying a series of recorded action potentials.
Exploring Compositional High Order Pattern Potentials for Structured Output Learning
In this work, we study the learning of a general class of pattern-like high order potential, which we call Compositional High Order Pattern Potentials (CHOPPs).
