Search Results for author:
Found 67 papers, 35 papers with code
Evolving Machine Learning: A Survey
Evolving Machine Learning (EML) has emerged as a critical paradigm, enabling continuous learning and adaptation in real-time data streams.
CrypticBio: A Large Multimodal Dataset for Visually Confusing Biodiversity
To highlight the importance of the dataset, we benchmark a suite of state-of-the-art foundation models across CrypticBio subsets of common, unseen, endangered, and invasive species, and demonstrate the substantial impact of geographical context on vision-language zero-shot learning for cryptic species.
AutoML Benchmark with shorter time constraints and early stopping
Automated Machine Learning (AutoML) automatically builds machine learning (ML) models on data.
Sculpting [CLS] Features for Pre-Trained Model-Based Class-Incremental Learning
Excessive plasticity in the models breaks generalizability and causes forgetting, while strong stability results in insufficient adaptation to new classes.
AILuminate: Introducing v1.0 of the AI Risk and Reliability Benchmark from MLCommons
This work represents a crucial step toward establishing global standards for AI risk and reliability evaluation while acknowledging the need for continued development in areas such as multiturn interactions, multimodal understanding, coverage of additional languages, and emerging hazard categories.
Occam's model: Selecting simpler representations for better transferability estimation
This problem is called transferability estimation.
On dataset transferability in medical image classification
These methods primarily focus on estimating the suitability of pre-trained source model features for a target dataset, which can lead to unrealistic predictions, such as suggesting that the target dataset is the best source for itself.
Continual Learning on a Data Diet
Continual Learning (CL) methods usually learn from all available data.
Learning to Learn without Forgetting using Attention
Continual learning (CL) refers to the ability to continually learn over time by accommodating new knowledge while retaining previously learned experience.
Can time series forecasting be automated? A benchmark and analysis
In the field of machine learning and artificial intelligence, time series forecasting plays a pivotal role across various domains such as finance, healthcare, and weather.
HyTAS: A Hyperspectral Image Transformer Architecture Search Benchmark and Analysis
Hyperspectral Imaging (HSI) plays an increasingly critical role in precise vision tasks within remote sensing, capturing a wide spectrum of visual data.
CLAMS: A System for Zero-Shot Model Selection for Clustering
We propose an AutoML system that enables model selection on clustering problems by leveraging optimal transport-based dataset similarity.
Unsupervised Meta-Learning via In-Context Learning
Unsupervised meta-learning aims to learn feature representations from unsupervised datasets that can transfer to downstream tasks with limited labeled data.
Introducing v0.5 of the AI Safety Benchmark from MLCommons
We created a new taxonomy of 13 hazard categories, of which 7 have tests in the v0. 5 benchmark.
Croissant: A Metadata Format for ML-Ready Datasets
Data is a critical resource for machine learning (ML), yet working with data remains a key friction point.
FOCIL: Finetune-and-Freeze for Online Class Incremental Learning by Training Randomly Pruned Sparse Experts
Class incremental learning (CIL) in an online continual learning setting strives to acquire knowledge on a series of novel classes from a data stream, using each data point only once for training.
Automatic Combination of Sample Selection Strategies for Few-Shot Learning
In few-shot learning, such as meta-learning, few-shot fine-tuning or in-context learning, the limited number of samples used to train a model have a significant impact on the overall success.
TrustLLM: Trustworthiness in Large Language Models
This paper introduces TrustLLM, a comprehensive study of trustworthiness in LLMs, including principles for different dimensions of trustworthiness, established benchmark, evaluation, and analysis of trustworthiness for mainstream LLMs, and discussion of open challenges and future directions.
DMLR: Data-centric Machine Learning Research -- Past, Present and Future
Drawing from discussions at the inaugural DMLR workshop at ICML 2023 and meetings prior, in this report we outline the relevance of community engagement and infrastructure development for the creation of next-generation public datasets that will advance machine learning science.
What Can AutoML Do For Continual Learning?
This position paper outlines the potential of AutoML for incremental (continual) learning to encourage more research in this direction.
Locality-Aware Hyperspectral Classification
Hyperspectral image classification is gaining popularity for high-precision vision tasks in remote sensing, thanks to their ability to capture visual information available in a wide continuum of spectra.
Ranked #1 on
Hyperspectral Image Classification
on Houston
(OA@15perclass metric)
Continual Learning with Dynamic Sparse Training: Exploring Algorithms for Effective Model Updates
Therefore, we perform a comprehensive study in which we investigate various DST components to find the best topology per task on well-known CIFAR100 and miniImageNet benchmarks in a task-incremental CL setup since our primary focus is to evaluate the performance of various DST criteria, rather than the process of mask selection.
Advances and Challenges in Meta-Learning: A Technical Review
This review provides a comprehensive technical overview of meta-learning, emphasizing its importance in real-world applications where data may be scarce or expensive to obtain.
MALIBO: Meta-learning for Likelihood-free Bayesian Optimization
Bayesian optimization (BO) is a popular method to optimize costly black-box functions.
Neural Architecture Search for Visual Anomaly Segmentation
This paper presents the first application of neural architecture search to the complex task of segmenting visual anomalies.
AdaCL:Adaptive Continual Learning
We show that adapting hyperpararmeters on each new task leads to improvement in accuracy, forgetting and memory.
Can Fairness be Automated? Guidelines and Opportunities for Fairness-aware AutoML
The field of automated machine learning (AutoML) introduces techniques that automate parts of the development of machine learning (ML) systems, accelerating the process and reducing barriers for novices.
Meta-Album: Multi-domain Meta-Dataset for Few-Shot Image Classification
We introduce Meta-Album, an image classification meta-dataset designed to facilitate few-shot learning, transfer learning, meta-learning, among other tasks.
Are Labels Needed for Incremental Instance Learning?
We propose VINIL, a self-incremental learner that can learn object instances sequentially, ii.
Automated Imbalanced Learning
Automated Machine Learning has grown very successful in automating the time-consuming, iterative tasks of machine learning model development.
Meta-Learning for Unsupervised Outlier Detection with Optimal Transport
Automated machine learning has been widely researched and adopted in the field of supervised classification and regression, but progress in unsupervised settings has been limited.
Evaluating Continual Test-Time Adaptation for Contextual and Semantic Domain Shifts
In this paper, our goal is to adapt a pre-trained convolutional neural network to domain shifts at test time.
AMLB: an AutoML Benchmark
Comparing different AutoML frameworks is notoriously challenging and often done incorrectly.
DataPerf: Benchmarks for Data-Centric AI Development
Machine learning research has long focused on models rather than datasets, and prominent datasets are used for common ML tasks without regard to the breadth, difficulty, and faithfulness of the underlying problems.
Open-Ended Learning Strategies for Learning Complex Locomotion Skills
Teaching robots to learn diverse locomotion skills under complex three-dimensional environmental settings via Reinforcement Learning (RL) is still challenging.
Warm-starting DARTS using meta-learning
Neural architecture search (NAS) has shown great promise in the field of automated machine learning (AutoML).
Advances in MetaDL: AAAI 2021 challenge and workshop
Winning methods featured various classifiers trained on top of the second last layer of popular CNN backbones, fined-tuned on the meta-training data (not necessarily in an episodic manner), then trained on the labeled support and tested on the unlabeled query sets of the meta-test data.
Online AutoML: An adaptive AutoML framework for online learning
For this purpose, we design an adaptive Online Automated Machine Learning (OAML) system, searching the complete pipeline configuration space of online learners, including preprocessing algorithms and ensembling techniques.
Automated Reinforcement Learning: An Overview
Automated RL provides a framework in which different components of RL including MDP modeling, algorithm selection and hyper-parameter optimization are modeled and defined automatically.
Frugal Machine Learning
Machine learning, already at the core of increasingly many systems and applications, is set to become even more ubiquitous with the rapid rise of wearable devices and the Internet of Things.
From Strings to Data Science: a Practical Framework for Automated String Handling
Many machine learning libraries require that string features be converted to a numerical representation for the models to work as intended.
Cats, not CAT scans: a study of dataset similarity in transfer learning for 2D medical image classification
There is currently no consensus on how to choose appropriate source data, and in the literature we can find both evidence of favoring large natural image datasets such as ImageNet, and evidence of favoring more specialized medical datasets.
Meta-Learning for Symbolic Hyperparameter Defaults
Hyperparameter optimization in machine learning (ML) deals with the problem of empirically learning an optimal algorithm configuration from data, usually formulated as a black-box optimization problem.
Fixed-point Quantization of Convolutional Neural Networks for Quantized Inference on Embedded Platforms
One drawback however is the high computational complexity and high memory consumption of CNNs which makes them unfeasible for execution on embedded platforms which are constrained on physical resources needed to support CNNs.
A comparison of optimisation algorithms for high-dimensional particle and astrophysics applications
Optimisation problems are ubiquitous in particle and astrophysics, and involve locating the optimum of a complicated function of many parameters that may be computationally expensive to evaluate.
Bayesian Optimisation
High Energy Physics - Phenomenology
Computational Physics
Hyperboost: Hyperparameter Optimization by Gradient Boosting surrogate models
Bayesian Optimization is a popular tool for tuning algorithms in automatic machine learning (AutoML) systems.
Theory-based Habit Modeling for Enhancing Behavior Prediction
Psychological theories of habit posit that when a strong habit is formed through behavioral repetition, it can trigger behavior automatically in the same environment.
Aerial Imagery Pixel-level Segmentation
Hence, we also propose a new benchmark on the DroneDeploy test set using the best performing DeepLabv3+ Xception65 architecture, with a mIOU score of 52. 5%.
Ranked #1 on
Semantic Segmentation
on DroneDeploy
Importance of Tuning Hyperparameters of Machine Learning Algorithms
The performance of many machine learning algorithms depends on their hyperparameter settings.
GAMA: a General Automated Machine learning Assistant
The General Automated Machine learning Assistant (GAMA) is a modular AutoML system developed to empower users to track and control how AutoML algorithms search for optimal machine learning pipelines, and facilitate AutoML research itself.
Adaptation Strategies for Automated Machine Learning on Evolving Data
To that end, we propose 6 concept drift adaptation strategies and evaluate their effectiveness on different AutoML approaches.
OpenML-Python: an extensible Python API for OpenML
It also provides functionality to conduct machine learning experiments, upload the results to OpenML, and reproduce results which are stored on OpenML.
An Open Source AutoML Benchmark
In recent years, an active field of research has developed around automated machine learning (AutoML).
A meta-learning recommender system for hyperparameter tuning: predicting when tuning improves SVM classifiers
For many machine learning algorithms, predictive performance is critically affected by the hyperparameter values used to train them.
MLSys: The New Frontier of Machine Learning Systems
Machine learning (ML) techniques are enjoying rapidly increasing adoption.
Better Trees: An empirical study on hyperparameter tuning of classification decision tree induction algorithms
DT induction algorithms present high predictive performance and interpretable classification models, though many HPs need to be adjusted.
Transformative Machine Learning
In all three problems, transformative machine learning significantly outperforms the best intrinsic representation.
Meta-Learning: A Survey
In this chapter, we provide an overview of the state of the art in this fascinating and continuously evolving field.
Characterizing classification datasets: a study of meta-features for meta-learning
These characterizations, also called meta-features, describe properties of the data which are predictive for the performance of machine learning algorithms trained on them.
ML-Schema: Exposing the Semantics of Machine Learning with Schemas and Ontologies
The ML-Schema, proposed by the W3C Machine Learning Schema Community Group, is a top-level ontology that provides a set of classes, properties, and restrictions for representing and interchanging information on machine learning algorithms, datasets, and experiments.
Layered TPOT: Speeding up Tree-based Pipeline Optimization
With the demand for machine learning increasing, so does the demand for tools which make it easier to use.
Meta-QSAR: a large-scale application of meta-learning to drug design and discovery
We first carried out the most comprehensive ever comparison of machine learning methods for QSAR learning: 18 regression methods, 6 molecular representations, applied to more than 2, 700 QSAR problems.
OpenML Benchmarking Suites
Machine learning research depends on objectively interpretable, comparable, and reproducible algorithm benchmarks.
OpenML: An R Package to Connect to the Machine Learning Platform OpenML
We show how the OpenML package allows R users to easily search, download and upload data sets and machine learning tasks.
ASlib: A Benchmark Library for Algorithm Selection
To address this problem, we introduce a standardized format for representing algorithm selection scenarios and a repository that contains a growing number of data sets from the literature.
OpenML: networked science in machine learning
Many sciences have made significant breakthroughs by adopting online tools that help organize, structure and mine information that is too detailed to be printed in journals.
Open science in machine learning
We present OpenML and mldata, open science platforms that provides easy access to machine learning data, software and results to encourage further study and application.
