This paper presents a new Graph Neural Network (GNN) type using feature-wise linear modulation (FiLM). Many standard GNN variants propagate information along the edges of a graph by computing "messages" based only on the representation of the source of each edge. In GNN-FiLM, the representation of the target node of an…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,694 papers · 148 categories
Trend · papers per month
33 results for “feature-wise”
We study the phenomenon of bias amplification in classifiers, wherein a machine learning model learns to predict classes with a greater disparity than the underlying ground truth. We demonstrate that bias amplification can arise via an inductive bias in gradient descent methods that results in the overestimation of the…
FLANs process each feature separately for better interpretability.
problem Need for interpretable machine learning models in critical scenarios.
method Feature-wise latent representations summed for prediction.
result FLANs enhance interpretability without sacrificing performance.
AdaTrans: Feature-wise and Sample-wise Adaptive Transfer Learning for High-dimensional Regressionstat.ML
AdaTrans adapts to feature and sample transfer in high-dimensional regression.
problem High-dimensional linear regression with more features than samples.
method F-AdaTrans and S-AdaTrans methods using fused-penalties and adaptive weights.
result AdaTrans achieves convergence rates close to oracle estimators and near-minimax optimal rates.
We introduce a general-purpose conditioning method for neural networks called FiLM: Feature-wise Linear Modulation. FiLM layers influence neural network computation via a simple, feature-wise affine transformation based on conditioning information. We show that FiLM layers are highly effective for visual reasoning - an…
The goal of supervised feature selection is to find a subset of input features that are responsible for predicting output values. The least absolute shrinkage and selection operator (Lasso) allows computationally efficient feature selection based on linear dependency between input features and output values. In this pa…
Learning representations that accurately capture long-range dependencies in sequential inputs -- including text, audio, and genomic data -- is a key problem in deep learning. Feed-forward convolutional models capture only feature interactions within finite receptive fields while recurrent architectures can be slow and …
Deviance-style normalization for sparse, jointly overdispersed count matrices
problem Jointly overdispersed count matrices
method Dirichlet-multinomial deviance residualization
result Preserves exact sparsity, evaluates in constant time, recovers multinomial residual
Improved multi-user VoiceFilter-Lite model for speech recognition.
problem Limited performance of multi-user VoiceFilter-Lite models.
method Dual learning rate schedule and FiLM for feature conditioning.
result Closed the performance gap between multi-user and single-user VoiceFilter-Lite models.
VJE learns latent representations without contrastive learning, providing probabilistic semantics.
problem Learning latent representations without contrastive signals.
method VJE maximizes a symmetric conditional evidence lower bound (ELBO) on paired encoder embeddings, using a Student-t distribution on a polar representation.
result VJE outperforms standard non-contrastive baselines in ImageNet-1K, CIFAR-10/100, and STL-10.
Learning Sequential Decisions from Multiple Sources via Group-Robust Markov Decision Processesstat.ME
Paper tackles robust decision-making from multiple sites with shared structure.
problem Learning robust sequential decisions from heterogeneous multi-site datasets.
method Group-Robust MDPs with d-rectangular uncertainty sets, feature-wise worst-case aggregation, and cluster-level pooling.
result Proves suboptimality bound for robust planning policy under robust partial coverage assumption.
We present an autoencoder that leverages learned representations to better measure similarities in data space. By combining a variational autoencoder with a generative adversarial network we can use learned feature representations in the GAN discriminator as basis for the VAE reconstruction objective. Thereby, we repla…
Gating Mechanisms for Combining Character and Word-level Word Representations: An Empirical Studycs.CL
In this paper we study how different ways of combining character and word-level representations affect the quality of both final word and sentence representations. We provide strong empirical evidence that modeling characters improves the learned representations at the word and sentence levels, and that doing so is par…
Fingerprinting-based positioning, one of the promising indoor positioning solutions, has been broadly explored owing to the pervasiveness of sensor-rich mobile devices, the prosperity of opportunistically measurable location-relevant signals and the progress of data-driven algorithms. One critical challenge is to contr…
Kernel testing compares cell states in single-cell data.
problem Comparing non-linear cell states in single-cell data.
method Kernel-based testing framework for non-linear distribution comparison.
result Identifies subtle population variations in cell states.
A family of recent successful approaches to few-shot learning relies on learning an embedding space in which predictions are made by computing similarities between examples. This corresponds to combining information between support and query examples at a very late stage of the prediction pipeline. Inspired by this obs…
CDSSL improves representation quality by integrating linear and nonlinear dependencies.
problem Scarcity of labeled data and neglect of nonlinear dependencies in SSL.
method CDSSL combines linear correlations and nonlinear dependencies using HSIC in RKHS.
result CDSSL enhances representation quality on diverse benchmarks.
Model predicts future values and fills in missing data.
problem Missing data in time series data.
method End-to-end time series model with two neural networks.
result Framework performs well in imputation and forecasting.
Recent breakthroughs in computer vision and natural language processing have spurred interest in challenging multi-modal tasks such as visual question-answering and visual dialogue. For such tasks, one successful approach is to condition image-based convolutional network computation on language via Feature-wise Linear …
EvoGrad improves efficiency in meta-learning and hyperparameter optimization.
problem Efficiently compute hypergradients for larger network architectures.
method Uses evolutionary techniques to estimate hypergradients without second-order derivatives or longer computational graphs.
result Significant improvements in efficiency, enabling scaling to bigger architectures.
New statistical methods improve explainability of boosting models.
problem Uncertainty quantification for boosting models is computationally intensive and hard to interpret.
method Derive methods for statistical inference using gradient boosting and Boulevard regularization.
result Achieve asymptotically normal predictions with theoretical guarantees and runtime independent of data size.
Image Super-Resolution with Cross-Scale Non-Local Attention and Exhaustive Self-Exemplars Miningcs.CV
This paper improves image super-resolution by integrating cross-scale non-local attention.
problem Improving image super-resolution by leveraging long-range and cross-scale feature correlations.
method Proposes a Cross-Scale Non-Local (CS-NL) attention module integrated into a recurrent neural network.
result Significantly improved performance on SISR benchmarks.
Paper proposes using pairwise feature comparisons to infer modification costs for user recourse.
problem Learning and inferring user preferences for modifying features in black-box models.
method Bradley-Terry model for inferring feature-wise costs from non-exhaustive human comparison surveys.
result Non-exhaustive human surveys can efficiently learn feature costs, enabling recourse finding.
DAG-FM discovers causal relationships from heterogeneous data.
problem Challenges in causal discovery from heterogeneous causal mechanisms.
method DAG-FM uses two specialized Transformer-based sub-modules and a robust tabular interaction block to model complex row-column interactions.
result DAG-FM achieves state-of-the-art performance on synthetic and real-world datasets.
Missing data imputation (MDI) is a fundamental problem in many scientific disciplines. Popular methods for MDI use global statistics computed from the entire data set (e.g., the feature-wise medians), or build predictive models operating independently on every instance. In this paper we propose a more general framework…
A hierarchical model shows how scaling laws emerge from sequential feature recovery.
problem Emergence of scaling laws from feature learning in multi-layer networks.
method Layer-wise spectral algorithm adapted to compositional structure, sequential feature detection.
result Sequential detection of latent features, leading to explicit power-law decay of prediction error.
Factorization Machine (FM) is a widely used supervised learning approach by effectively modeling of feature interactions. Despite the successful application of FM and its many deep learning variants, treating every feature interaction fairly may degrade the performance. For example, the interactions of a useless featur…
Proposes Geodesic Integrated Gradients (GIG) for more accurate feature attributions in deep networks.
problem Flawed attributions using straight paths from Integrated Gradients (IG).
method Introduces a model-induced Riemannian metric and computes attributions along geodesics.
result GIG produces more faithful attributions than IG on benchmarks.
Deep learning involves a difficult non-convex optimization problem with a large number of weights between any two adjacent layers of a deep structure. To handle large data sets or complicated networks, distributed training is needed, but the calculation of function, gradient, and Hessian is expensive. In particular, th…
A new method simplifies feature explanation for complex models.
problem Explain predictions from complex models efficiently with many features.
method groupShapley: groups features for Shapley value computation.
result Equivalent to summing feature-wise Shapley values within groups.
Unified normative modeling for neuroimaging phenotypes using denoising diffusion models.
problem Discarding multivariate dependence in neuroimaging pipelines.
method Denoising diffusion probabilistic models (DDPMs) with FiLM and SAINT backbones.
result Unified multivariate normative modeling with better calibration and dependence preservation.
TRACER improves interpretability in high stakes analytics.
problem Interpreting complex models in high stakes applications.
method TRACER framework with TITV model for healthcare analytics.
result TRACER facilitates both accurate and interpretable analytics.
New method learns PDE solutions from low-fidelity data.
problem Challenges in learning PDE surrogates with scarce data.
method Flow matching in infinite-dimensional space with conditional neural operators.
result Accurately learns PDE solutions across different resolutions and fidelities.