Search Results for author:
Found 40 papers, 16 papers with code
Compositional Generalization for Kinship Prediction through Data Augmentation
However, predicting and using intermediate kinship graphs leads to a deterioration in the generalization of kinship prediction by around 50% on average relative to models that only leverage data augmentation.
Interpretable Multi-Source Data Fusion Through Latent Variable Gaussian Process
Towards resolving this issue, a multi-source data fusion framework based on Latent Variable Gaussian Process (LVGP) is proposed.
Leveraging Multiple Teachers for Test-Time Adaptation of Language-Guided Classifiers
Recent approaches have explored language-guided classifiers capable of classifying examples from novel tasks when provided with task-specific natural language explanations, instructions or prompts (Sanh et al., 2022; R. Menon et al., 2022).
Pragmatic Reasoning Unlocks Quantifier Semantics for Foundation Models
Generalized quantifiers (e. g., few, most) are used to indicate the proportions predicates are satisfied (for example, some apples are red).
Beyond Labels: Empowering Human Annotators with Natural Language Explanations through a Novel Active-Learning Architecture
Our AL architecture leverages an explanation-generation model to produce explanations guided by human explanations, a prediction model that utilizes generated explanations toward prediction faithfully, and a novel data diversity-based AL sampling strategy that benefits from the explanation annotations.
Bridging Nations: Quantifying the Role of Multilinguals in Communication on Social Media
Social media enables the rapid spread of many kinds of information, from memes to social movements.
Green Federated Learning
The rapid progress of AI is fueled by increasingly large and computationally intensive machine learning models and datasets.
When does the student surpass the teacher? Federated Semi-supervised Learning with Teacher-Student EMA
Semi-Supervised Learning (SSL) has received extensive attention in the domain of computer vision, leading to development of promising approaches such as FixMatch.
Pruning Compact ConvNets for Efficient Inference
The resulting family of pruned models can consistently obtain better performance than existing FBNetV3 models at the same level of computation, and thus provide state-of-the-art results when trading off between computational complexity and generalization performance on the ImageNet benchmark.
LaSQuE: Improved Zero-Shot Classification from Explanations Through Quantifier Modeling and Curriculum Learning
A hallmark of human intelligence is the ability to learn new concepts purely from language.
A Comprehensive Review of Digital Twin -- Part 2: Roles of Uncertainty Quantification and Optimization, a Battery Digital Twin, and Perspectives
This second paper presents a literature review of key enabling technologies of digital twins, with an emphasis on uncertainty quantification, optimization methods, open source datasets and tools, major findings, challenges, and future directions.
A Comprehensive Review of Digital Twin -- Part 1: Modeling and Twinning Enabling Technologies
In part two of this review, the role of uncertainty quantification and optimization are discussed, a battery digital twin is demonstrated, and more perspectives on the future of digital twin are shared.
Reconciling Security and Communication Efficiency in Federated Learning
Cross-device Federated Learning is an increasingly popular machine learning setting to train a model by leveraging a large population of client devices with high privacy and security guarantees.
Pulse Shape Simulation and Discrimination using Machine-Learning Techniques
Pulse shape discrimination (PSD) is a basic method for this purpose in many nuclear, high-energy, and rare-event search experiments where scintillator detectors are used.
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
BIG-bench focuses on tasks that are believed to be beyond the capabilities of current language models.
CLUES: A Benchmark for Learning Classifiers using Natural Language Explanations
For this, we introduce CLUES, a benchmark for Classifier Learning Using natural language ExplanationS, consisting of a range of classification tasks over structured data along with natural language supervision in the form of explanations.
Learning to Mediate Disparities Towards Pragmatic Communication
The PRS attempts to learn the speaker-listener disparity and adjust the speech accordingly, by adding a light-weighted disparity adjustment layer into working memory on top of speaker's long-term memory system.
Reinforcement Learning based Sequential Batch-sampling for Bayesian Optimal Experimental Design
In such scenarios, one usually resorts to performing experiments in a manner that allows for maximizing one's state-of-knowledge while satisfying the above mentioned practical constraints.
Mapping Language to Programs using Multiple Reward Components with Inverse Reinforcement Learning
On the VirtualHome framework, we get improvements of up to 9. 0% on the Longest Common Subsequence metric and 14. 7% on recall-based metrics over previous work on this framework (Puig et al., 2018).
Opacus: User-Friendly Differential Privacy Library in PyTorch
We introduce Opacus, a free, open-source PyTorch library for training deep learning models with differential privacy (hosted at opacus. ai).
Adversarial Scrubbing of Demographic Information for Text Classification
Contextual representations learned by language models can often encode undesirable attributes, like demographic associations of the users, while being trained for an unrelated target task.
ePiC: Employing Proverbs in Context as a Benchmark for Abstract Language Understanding
While large language models have shown exciting progress on several NLP benchmarks, evaluating their ability for complex analogical reasoning remains under-explored.
Inverse Aerodynamic Design of Gas Turbine Blades using Probabilistic Machine Learning
One of the critical components in Industrial Gas Turbines (IGT) is the turbine blade.
How Helpful is Inverse Reinforcement Learning for Table-to-Text Generation?
Many approaches to this problem use Reinforcement Learning (RL), which maximizes a single manually defined reward, such as BLEU.
Detecting Cross-Geographic Biases in Toxicity Modeling on Social Media
Online social media platforms increasingly rely on Natural Language Processing (NLP) techniques to detect abusive content at scale in order to mitigate the harms it causes to their users.
Importance-based Multimodal Autoencoder
In this paper we propose the IMA (Importance-based Multimodal Autoencoder) model, a scalable model that learns modality importances and robust multimodal representations through a novel cross-covariance based loss function.
Data-based Discovery of Governing Equations
Without a prior definition of the model structure, first a free-form of the equation is discovered, and then calibrated and validated against the available data.
PRover: Proof Generation for Interpretable Reasoning over Rules
First, PROVER generates proofs with an accuracy of 87%, while retaining or improving performance on the QA task, compared to RuleTakers (up to 6% improvement on zero-shot evaluation).
Data-Informed Decomposition for Localized Uncertainty Quantification of Dynamical Systems
The region of interest can be specified based on the localization features of the solution, user interest, and correlation length of the random material properties.
A Fully Bayesian Gradient-Free Supervised Dimension Reduction Method using Gaussian Processes
The comparison shows that the proposed method improves the active subspace recovery and predictive accuracy, in both the deterministic and probabilistic sense, when only few model observations are available for training, at the cost of increased training time.
Bayesian learning of orthogonal embeddings for multi-fidelity Gaussian Processes
We present a Bayesian approach to identify optimal transformations that map model input points to low dimensional latent variables.
Analysing the Extent of Misinformation in Cancer Related Tweets
This helps spread awareness regarding the various causes, cures and prevention methods of cancer.
Advances in Bayesian Probabilistic Modeling for Industrial Applications
The methodology, called GE's Bayesian Hybrid Modeling (GEBHM), is a probabilistic modeling method, based on the Kennedy and O'Hagan framework, that has been continuously scaled-up and industrialized over several years.
Bayesian task embedding for few-shot Bayesian optimization
We describe a method for Bayesian optimization by which one may incorporate data from multiple systems whose quantitative interrelationships are unknown a priori.
A Strategy for Adaptive Sampling of Multi-fidelity Gaussian Process to Reduce Predictive Uncertainty
Multi-fidelity Gaussian process is a common approach to address the extensive computationally demanding algorithms such as optimization, calibration and uncertainty quantification.
Wetin dey with these comments? Modeling Sociolinguistic Factors Affecting Code-switching Behavior in Nigerian Online Discussions
Multilingual individuals code switch between languages as a part of a complex communication process.
DeepTagRec: A Content-cum-User based Tag Recommendation Framework for Stack Overflow
In this paper, we develop a content-cum-user based deep learning framework DeepTagRec to recommend appropriate question tags on Stack Overflow.
Public Sphere 2.0: Targeted Commenting in Online News Media
Because the readers lack the time to go over an entire article, most of the comments are relevant to only particular sections of an article.
Affect-LM: A Neural Language Model for Customizable Affective Text Generation
Human verbal communication includes affective messages which are conveyed through use of emotionally colored words.
Learning Representations of Affect from Speech
Experiments on a well-established real-life speech dataset (IEMOCAP) show that the learnt representations are comparable to state of the art feature extractors (such as voice quality features and MFCCs) and are competitive with state-of-the-art approaches at emotion and dimensional affect recognition.
