Dataset of 4500 bicycle designs aids in design analysis and synthesis.
problem Identify gaps in bicycle market and design space, classify bicycles, synthesize new designs.
method Processed dataset, unsupervised dimensionality reduction, supervised classification, machine learning synthesis.
result Identified design parameters and factors influencing bicycle classification.
This paper addresses challenges in designing datasets for autonomous driving.
problem Lack of robust datasets suitable for industrial deployment.
method Identifies common issues and steps to avoid them.
result Encourages better formalization of dataset design in the scientific community.
QCircuitBench provides a dataset for evaluating AI's ability to design quantum algorithms.
problem Lack of datasets for evaluating AI's capability in designing quantum algorithms.
method Developed a comprehensive benchmark dataset with 120,290 data points, including 25 algorithms and 3 task suites.
result LLMs exhibit consistent error patterns and fine-tuning does not always outperform few-shot learning.
A framework for faster, better infographic design by non-experts and experts alike.
problem Designing infographics is time-consuming and tedious for non-experts and even professionals.
method Semi-automated infographic framework for structured and flow-based designs, including automatic design ranking and customization options.
result Designers from all expertise levels can generate generic infographic designs faster than existing methods while maintaining quality.
Deep learning models enhance engineering design automation.
problem Design optimization and customization across various industries.
method Leveraging deep neural networks, GANs, VAEs, and DRL for design synthesis.
result Recent advances in DGMs show promise in structural optimization, materials design, and shape synthesis.
PropEn uses matching to create a larger dataset for efficient design optimization.
problem Limited data and complex landscapes in scientific applications.
method PropEn uses a matching approach to implicitly guide design without a discriminator.
result PropEn efficiently approximates the gradient of property improvement within the data distribution.
SketchGraphs dataset aids in modeling CAD designs.
problem Training models to reason about CAD designs efficiently.
method Collection of 15 million sketches with geometric constraint graphs.
result Demonstrated use cases for generative modeling and conditional generation.
An associative memory is a framework of content-addressable memory that stores a collection of message vectors (or a dataset) over a neural network while enabling a neurally feasible mechanism to recover any message in the dataset from its noisy version. Designing an associative memory requires addressing two main task…
Paper proposes a new method for designing materials using deep learning.
problem Designing high-performance material distributions from given distributions.
method Iterative process of selecting, generating, and merging material distributions using a deep generative model.
result The method improves material performance through iterative refinement.
Enhances scenario approach for certifying design properties post-design.
problem Certifying additional useful properties in designs not considered during the design phase.
method Two-level framework of appropriateness: baseline and post-design. Distribution-free upper bounds on risk derived.
result Distribution-free upper bounds on the risk of failing to meet post-design appropriateness.
Study shows partially-typed NER datasets can match fully-typed ones in model performance.
problem Leveraging multiple partially-typed NER datasets for training models without fully-typed annotations.
method Systematic analysis and controlled experiments comparing partially-typed and fully-typed datasets.
result Models trained with partially-typed annotations can achieve similar performance to those trained with fully-typed annotations.
We consider the problem of designing a sparse Gaussian process classifier (SGPC) that generalizes well. Viewing SGPC design as constructing an additive model like in boosting, we present an efficient and effective SGPC design method to perform a stage-wise optimization of a predictive loss function. We introduce new me…
Deep learning predicts patient trajectories in open Mimic-III dataset.
problem Predicting future medical conditions from patient history.
method Two parallel bi-directional Minimal Gated Recurrent Unit networks trained on Mimic-III dataset.
result Significant improvements in automated medical prognosis measured by Recall@k.
Automates supervised learning pipeline design with matrix and tensor factorization.
problem Designing effective supervised learning pipelines with many choices.
method Uses matrix and tensor factorization to model pipeline search space and develops greedy experiment design protocols.
result Demonstrates the effectiveness of the approach on real-world classification problems.
Grale designs graphs for graph learning, improving performance on large datasets.
problem Finding the right graph for semi-supervised learning with billions of nodes.
method Fuses multiple similarity measures using locality sensitive hashing to create task-specific graphs.
result Grale detects a large number of malicious actors, increasing recall by 89%.
Algorithm improves reinforcement learning policies using offline data.
problem Improving reinforcement learning policies with limited online data.
method Designs a single non-reactive policy using offline data with provable guarantees.
result Algorithm achieves better policy quality with less online data.
Designs a single policy for collecting data to train near-optimal policies.
problem Engineering overhead in deploying minimax procedures for stochastic linear contextual bandits.
method Designs a single stochastic policy to collect data from which a near-optimal policy can be extracted.
result The designed policy can collect data from which a near-optimal policy can be extracted.
New layer improves neural networks' flexibility and speed.
problem Designing efficient neural networks for real-time learning.
method Sparse Associative Memories for incremental learning.
result Improved Neural Networks with faster training and real-time support.
METASET selects diverse unit cells for efficient data-driven metamaterial design.
problem Imbalanced datasets in unit cells can bias data-driven metamaterial design.
method METASET uses similarity metrics and DPPs to select diverse subsets of unit cells.
result Smaller, diverse subsets improve search process and structural performance.
New framework shows diverse training data improves subgroup and overall performance.
problem Lack of understanding how diverse training data affects subgroup and overall performance.
method Casts data collection as part of the learning process, analyzes dataset compositions, and guides dataset design.
result Diverse representation in training data improves subgroup and overall performance.
A similarity metric for icon sets simplifies design selection.
problem Designing optimal icon sets is challenging and requires expert knowledge.
method Proposed a Siamese Neural Network trained on human-rated data.
result The model effectively captures style and visual identity similarities.
Unified framework for robust A/B testing under model misspecification.
problem Improving sample efficiency in A/B testing with model misspecification.
method Unified framework for contextual bandit and dynamic settings, proving worst-case mean squared error bounds.
result Empirically validated approach using synthetic and real-world datasets.
A method to select validation data from a dataset using statistical criteria.
problem Selecting a validation basis from a full dataset for machine learning model validation.
method Adopting a 'design of experiments' point of view and using statistical criteria, particularly Maximum Mean Discrepancy criteria.
result The 'support points' concept is particularly relevant for selecting validation data.
Horizon is Facebook's open RL platform for large, slow feedback datasets.
problem Training RL models with large, slow feedback datasets.
method End-to-end RL platform with workflows, data preprocessing, distributed training, etc.
result RL models trained with Horizon significantly outperform supervised learning systems.
Predicts optimal training dataset sizes per class for machine learning models.
problem Optimizing training dataset sizes for class-specific machine learning models.
method Algorithm based on space-filling design of experiments, models like powerlaw curves and generalized linear models.
result The algorithm predicts optimal training dataset sizes per class for improved model performance.
In this paper, we present Paranom, a parallel anomaly dataset generator. We discuss its design and provide brief experimental results demonstrating its usefulness in improving the classification correctness of LSTM-AD, a state-of-the-art anomaly detection model.
Scalable GP model tackles big data, categorical factors, and multiple responses.
problem Handling big datasets, categorical inputs, and multiple responses in Gaussian processes.
method Latent variable Gaussian process (LVGP) with variational inference for scalability and interpretability.
result The method scales well for large datasets and outperforms state-of-the-art methods.
Study on shortcuts in deep networks, revealing their layer-wise distribution and impact.
problem Understudied impact of shortcuts on feature representations in deep networks.
method Layer-wise localization through counterfactual training on clean and skewed datasets.
result Shortcuts are distributed throughout the network, not localized in specific layers.
In high dimensions, most machine learning methods are brittle to even a small fraction of structured outliers. To address this, we introduce a new meta-algorithm that can take in a base learner such as least squares or stochastic gradient descent, and harden the learner to be resistant to outliers. Our method, Sever, p…
We introduce Bayesian optimization, a technique developed for optimizing time-consuming engineering simulations and for fitting machine learning models on large datasets. Bayesian optimization guides the choice of experiments during materials design and discovery to find good material designs in as few experiments as p…
MET learns tabular data representations without data augmentations.
problem Lack of effective self-supervised learning methods for tabular data.
method Reconstruction-based approach using masked encoding, with separate representations for each coordinate and adversarial reconstruction loss.
result MET achieves state-of-the-art performance on five diverse tabular datasets, improving up to 9% over current methods.
Generative model for scalable vector graphics captures font design statistics.
problem Lack of higher-level understanding in vision and imagery modeling.
method Sequential generative models of vector graphics.
result Model captures statistical dependencies and richness of font datasets.
FairBED: A Bayesian Experimental Design Approach to Gathering Fairer Data
problem Ensuring fairness in machine learning
method Bayesian Experimental Design
result Improved fairness-accuracy trade-offs
Algorithm optimizes biological sequences using bootstrapped training with a score-conditioned generator.
problem Optimizing biological sequences for a black-box score function.
method Bootstrapped training of score-conditioned generator (BootGen) algorithm.
result Our method outperforms competitive baselines on biological sequential design tasks.
FinML-Chain integrates blockchain data for financial machine learning.
problem Challenges in financial machine learning, including missing data, lack of transparency, and incompatible data sources.
method Blockchain technology integrated with machine learning techniques to address financial market challenges.
result Framework generates datasets for analyzing economic mechanisms, advancing financial research.
New benchmarks for offline RL from diverse datasets.
problem Measuring progress in offline RL due to lack of suitable benchmarks.
method Developed benchmarks tailored for offline RL, focusing on diverse dataset properties.
result Revealed deficiencies in existing offline RL algorithms.
LBO optimizes model selection for evolving datasets.
problem Model selection for datasets arriving and evolving over time.
method Online, multitask Bayesian optimization exploiting function correlation.
result LBO outperforms standard BO algorithms on real and synthetic data.
A new framework promotes trustworthy user-generated datasets by ensuring no user benefits from misreporting.
problem Incentivizing data misreporting in user-generated datasets.
method Proposes Licchavi, a global and personalized learning framework with provable strategyproofness guarantees.
result Proves that no user can gain much by replying to Licchavi's queries with deviated answers.
Benchmark study evaluates 8 clustering methods on 99 UCR time series datasets.
problem Assessing the performance of clustering methods on time series data.
method Examines 8 clustering methods across 3 categories and 3 distance measures on 99 UCR datasets.
result Provides a comprehensive dataset-level assessment of clustering methods.
This work introduces benchmarks for evaluating nanophotonic structures in design simulations.
problem Design and understanding of nanophotonic structures for various applications.
method Development of frameworks and benchmarks for evaluating nanophotonic structures in parametric design problems.
result Strategic use of evaluation fidelity in enhancing structure designs.
Experiments used in current continual learning research do not faithfully assess fundamental challenges of learning continually. Instead of assessing performance on challenging and representative experiment designs, recent research has focused on increased dataset difficulty, while still using flawed experiment set-ups…
Study shows different trajectory prediction models generalize better under OoD conditions.
problem Comparing trajectory prediction models' robustness across different datasets.
method Training models on Argoverse 2 and testing on Waymo Open Motion, and vice versa, with various augmentation strategies.
result Smallest model with highest inductive bias performs best in OoD generalization.
Improved graph attention model for noisy graphs.
problem Understanding and improving graph attention in noisy graphs.
method Proposes SuperGAT, a self-supervised graph attention network.
result SuperGAT learns more expressive attention by encoding edges.
A new model designs molecular latent vectors for drug discovery.
problem Designing effective molecular descriptors from molecular structures.
method Proposes a denoising diffusion probabilistic model (DDPM) for variational autoencoding molecular graphs.
result Demonstrates superior prediction performance and robustness compared to existing approaches.
With an abundance of research papers in deep learning, reproducibility or adoption of the existing works becomes a challenge. This is due to the lack of open source implementations provided by the authors. Further, re-implementing research papers in a different library is a daunting task. To address these challenges, w…
Efficient decoder design improves semantic segmentation for real-time automated driving.
problem Efficient design of decoders for real-time semantic segmentation in automated driving.
method Design of a novel non-bottleneck layer and family of decoders using VGG10 as an efficient encoder.
result Improvement of 10% in performance compared to a baseline.
Developing neural network image classification models often requires significant architecture engineering. In this paper, we study a method to learn the model architectures directly on the dataset of interest. As this approach is expensive when the dataset is large, we propose to search for an architectural building bl…
Automates translating natural language to Verilog for digital design.
problem Manual translation of natural language specifications to Verilog is time-consuming and error-prone.
method Fine-tuned GPT-2 to derive Verilog from English, using a dataset of design tasks.
result GPT-2 achieved 94.8% correct translation across simple and abstract design tasks.