Search Results for author:
Found 38 papers, 21 papers with code
Stronger Than You Think: Benchmarking Weak Supervision on Realistic Tasks
Weak supervision (WS) is a popular approach for label-efficient learning, leveraging diverse sources of noisy but inexpensive weak labels to automatically annotate training data.
Evaluating Sample Utility for Data Selection by Mimicking Model Weights
Instead, we propose a new approach, Mimic Score, a data quality metric that uses a pretrained reference model as a guide to assess the usefulness of data samples for training a new model.
Weak-to-Strong Generalization Through the Data-Centric Lens
The weak-to-strong generalization phenomenon is the driver for important machine learning applications including highly data-efficient learning and, most recently, performing superalignment.
MoRe Fine-Tuning with 10x Fewer Parameters
Parameter-efficient fine-tuning (PEFT) techniques have unlocked the potential to cheaply and easily specialize large pretrained models.
Evaluating Language Model Context Windows: A "Working Memory" Test and Inference-time Correction
Large language models are prominently used in real-world applications, often tasked with reasoning over large volumes of documents.
Is Free Self-Alignment Possible?
Aligning pretrained language models (LMs) is a complex and resource-intensive process, often requiring access to large amounts of ground-truth preference data and substantial compute.
Pretrained Hybrids with MAD Skills
Manticore $\textit{automates the design of hybrid architectures}$ while reusing pretrained models to create $\textit{pretrained}$ hybrids.
Pearls from Pebbles: Improved Confidence Functions for Auto-labeling
We develop a tractable version of the framework to obtain \texttt{Colander} (Confidence functions for Efficient and Reliable Auto-labeling), a new post-hoc method specifically designed to maximize performance in TBAL systems.
OTTER: Effortless Label Distribution Adaptation of Zero-shot Models
Popular zero-shot models suffer due to artifacts inherited from pretraining.
Product Manifold Representations for Learning on Biological Pathways
Machine learning models that embed graphs in non-Euclidean spaces have shown substantial benefits in a variety of contexts, but their application has not been studied extensively in the biological domain, particularly with respect to biological pathway graphs.
Multimodal Data Curation via Object Detection and Filter Ensembles
We propose an approach for curating multimodal data that we used for our entry in the 2023 DataComp competition filtering track.
Train 'n Trade: Foundations of Parameter Markets
Organizations typically train large models individually.
The Cost of Compression: Investigating the Impact of Compression on Parametric Knowledge in Language Models
Two standard compression techniques are pruning and quantization, with the former eliminating redundant connections in model layers and the latter representing model parameters with fewer bits.
Zero-Shot Robustification of Zero-Shot Models
Additionally, we demonstrate that RoboShot is compatible with a variety of pretrained and language models and propose a way to further boost performance with a zero-shot adaptation variant.
Mitigating Source Bias for Fairer Weak Supervision
Weak supervision enables efficient development of training sets by reducing the need for ground truth labels.
Domain Generalization via Nuclear Norm Regularization
In this paper, we propose a simple and effective regularization method based on the nuclear norm of the learned features for domain generalization.
Resonant Anomaly Detection with Multiple Reference Datasets
An important class of techniques for resonant anomaly detection in high energy physics builds models that can distinguish between reference and target datasets, where only the latter has appreciable signal.
Lifting Weak Supervision To Structured Prediction
Weak supervision (WS) is a rich set of techniques that produce pseudolabels by aggregating easily obtained but potentially noisy label estimates from a variety of sources.
Promises and Pitfalls of Threshold-based Auto-labeling
Given the long shelf-life and diverse usage of the resulting datasets, understanding when the data obtained by such auto-labeling systems can be relied on is crucial.
AutoML for Climate Change: A Call to Action
The challenge that climate change poses to humanity has spurred a rapidly developing field of artificial intelligence research focused on climate change applications.
Ask Me Anything: A simple strategy for prompting language models
Prompting is a brittle process wherein small modifications to the prompt can cause large variations in the model predictions, and therefore significant effort is dedicated towards designing a painstakingly "perfect prompt" for a task.
Ranked #1 on
Question Answering
on Story Cloze
AutoWS-Bench-101: Benchmarking Automated Weak Supervision with 100 Labels
While it has been used successfully in many domains, weak supervision's application scope is limited by the difficulty of constructing labeling functions for domains with complex or high-dimensional features.
Shoring Up the Foundations: Fusing Model Embeddings and Weak Supervision
Despite the black-box nature of foundation models, we prove results characterizing how our approach improves performance and show that lift scales with the smoothness of label distributions in embedding space.
Generative Modeling Helps Weak Supervision (and Vice Versa)
The model outperforms baseline weak supervision label models on a number of multiclass image classification datasets, improves the quality of generated images, and further improves end-model performance through data augmentation with synthetic samples.
Universalizing Weak Supervision
We apply this technique to important problems previously not tackled by WS frameworks including learning to rank, regression, and learning in hyperbolic space.
NAS-Bench-360: Benchmarking Neural Architecture Search on Diverse Tasks
This makes the performance of NAS approaches in more diverse areas poorly understood.
Comparing the Value of Labeled and Unlabeled Data in Method-of-Moments Latent Variable Estimation
We apply our decomposition framework to three scenarios -- well-specified, misspecified, and corrected models -- to 1) choose between labeled and unlabeled data and 2) learn from their combination.
Cut out the annotator, keep the cutout: better segmentation with weak supervision
We propose a framework that fuses limited label learning and weak supervision for segmentation tasks, enabling users to train high-performing segmentation CNNs with very few hand-labeled training points.
Train and You'll Miss It: Interactive Model Iteration with Weak Supervision and Pre-Trained Embeddings
Our goal is to enable machine learning systems to be trained interactively.
Low-Dimensional Hyperbolic Knowledge Graph Embeddings
However, existing hyperbolic embedding methods do not account for the rich logical patterns in KGs.
Ranked #5 on
Link Prediction
on YAGO3-10
Ivy: Instrumental Variable Synthesis for Causal Inference
To relax these assumptions, we propose Ivy, a new method to combine IV candidates that can handle correlated and invalid IV candidates in a robust manner.
Fast and Three-rious: Speeding Up Weak Supervision with Triplet Methods
In this work, we show that, for a class of latent variable models highly applicable to weak supervision, we can find a closed-form solution to model parameters, obviating the need for iterative solutions like stochastic gradient descent (SGD).
Multi-Resolution Weak Supervision for Sequential Data
Multi-resolution sources exacerbate this challenge due to complex correlations and sample complexity that scales in the length of the sequence.
Learning Mixed-Curvature Representations in Product Spaces
The quality of the representations achieved by embeddings is determined by how well the geometry of the embedding space matches the structure of the data.
Learning Dependency Structures for Weak Supervision Models
Labeling training data is a key bottleneck in the modern machine learning pipeline.
Training Complex Models with Multi-Task Weak Supervision
Snorkel MeTaL: A framework for training models with multi-task weak supervision
Ranked #1 on
Semantic Textual Similarity
on SentEval
Representation Tradeoffs for Hyperbolic Embeddings
Given a tree, we give a combinatorial construction that embeds the tree in hyperbolic space with arbitrarily low distortion without using optimization.
Don't Fear the Bit Flips: Optimized Coding Strategies for Binary Classification
After being trained, classifiers must often operate on data that has been corrupted by noise.
