A new method scales sparse machine learning to ultra-high dimensional problems.
problem Sparse and interpretable machine learning in ultra-high dimensional data.
method Two-phase approach: backbone set determination followed by reduced problem solving.
result The backbone set contains truly relevant features with high probability.
We detect the backbone of the weighted bipartite network of the Japanese credit market relationships. The backbone is detected by adapting a general method used in the investigation of weighted networks. With this approach we detect a backbone that is statistically validated against a null hypothesis of uniform diversi…
Researchers use shape analysis to recover protein structures from Cryo-EM data.
problem Recovering the three-dimensional backbone structure of single polypeptide proteins from noisy tomographic projections.
method Shape analysis and matrix Lie group actions to deform point clouds to match 2D tomography data.
result Optimal deformations are computed to recover the three-dimensional backbone structure of proteins.
A new diffusion model generates novel protein backbones without relying on pretrained networks.
problem Generating novel protein backbones without relying on pretrained networks.
method Developed a SE(3) invariant diffusion model on multiple frames, called FrameDiff.
result Generated designable protein monomers up to 500 amino acids without pretrained networks.
Deep forecasting models show output heads significantly improve performance on fat-tailed financial returns.
problem Improving deep learning models for forecasting fat-tailed financial returns.
method Comparison of backbone architectures and output heads (point, Gaussian, Gaussian mixture) on S&P 500 monthly log-returns.
result Switching from point to Gaussian heads improves CRPS by about 1.3 percent, and from Gaussian to mixture adds another 2.4 percent.
In this paper, we investigate the statistical features of the weighted international-trade network. By finding the maximum weight spanning trees for this network we make the extraction of the truly relevant connections forming the network's backbone. We discuss the role of large-sized countries (strongest economies) in…
New method learns diverse protein scaffolds for motif design.
problem Designing long, diverse protein scaffolds for specific motifs.
method E(3)-equivariant graph neural network for diffusion modeling.
result First to guarantee conditional sampling from diffusion models.
New approach uses contrastive learning for better wireless power control.
problem Improving power control in wireless networks.
method A multi-layer perceptron with a contrastive learning backbone and head.
result Significant gains in sum-throughput and sample efficiency over supervised learning.
Generative model designs highly designable proteins using geometric algebra.
problem Creating proteins with diverse and statistically accurate secondary structures.
method Introduced a geometric algebra flow matching model (FrameFlow) with Clifford Frame Attention (CFA) for protein backbone design.
result Achieved high designability, diversity, and novelty in protein backbone sampling.
MTL-NAS combines NAS with GP-MTL for task-agnostic multi-task learning.
problem Designing architectures for diverse tasks with varying priors.
method Disentangled GP-MTL networks, hierarchical feature sharing, and gradient-based search.
result General-purpose model trained once can adapt to multiple tasks.
Few-step protein backbone generators reduce sampling time by over 20x.
problem Computational bottleneck in diffusion-based protein generation models.
method Score distillation adapted for protein backbone generation, combined with inference time noise modulation.
result Significant reduction in sampling time (20+ fold) while maintaining comparable performance.
Structural and topological information play a key role in modeling flow and transport through fractured rock in the subsurface. Discrete fracture network (DFN) computational suites such as dfnWorks are designed to simulate flow and transport in such porous media. Flow and transport calculations reveal that a small back…
Correlation Networks (CNs) inherently suffer from redundant information in their network topology. Bayesian Networks (BNs), on the other hand, include only non-redundant information (from a probabilistic perspective) resulting in a sparse topology from which generalizable physical features can be extracted. We advocate…
BackboneLearn speeds up MIO-based machine learning problems.
problem Scaling mixed-integer optimization problems in machine learning.
method An open-source Python framework for MIO problems with indicator variables.
result Solves MIO problems faster and more accurately than existing methods.
RPN 2 improves function learning by modeling data interdependence.
problem Invalid assumption of input data independence leads to performance degradation.
method Integrates data and structural interdependence functions into RPN 2's architecture.
result Significantly improves learning performance and expands unifying potential.
GAPA method provides efficient uncertainty quantification for pretrained networks.
problem Reliable uncertainty estimates for pretrained models are challenging.
method Post-hoc Gaussian Process Activations (GAPA) method that shifts Bayesian modeling from weights to activations.
result GAPA method provides efficient uncertainty quantification without altering the backbone's predictions.
BiTAT improves neural network quantization for edge devices by focusing on weight dependencies and disentangling them.
problem Performance degradation of compact neural networks under extreme quantization.
method Task-dependent Aggregated Transformation (BiTAT) method that orthonormalizes weights and progressively quantizes them.
result BiTAT effectively preserves model performance on ImageNet and CIFAR-100 with compact backbones.
Optimizes neural networks' last layer with closed-form solutions.
problem Optimizing neural networks' last layer with stochastic gradient descent.
method Adapting closed-form last layer optimization for stochastic gradient descent, alternating between backbone and last layer updates.
result The method converges to optimal solutions and outperforms standard SGD and Adam in regression tasks.
Reinforcement Patching optimizes dynamic sequence patching for efficient time series forecasting.
problem Efficiently learning data-adaptive representations for long-horizon sequence data, especially continuous sequences.
method Reinforcement Patching (ReinPatch) uses reinforcement learning to optimize dynamic patching policies and sequence backbones.
result ReinPatch achieves compelling performance in time-series forecasting compared to state-of-the-art methods.
V-HMN integrates memory mechanisms for improved image recognition.
problem Limited interpretability and high data requirements of existing vision backbones.
method Brain-inspired hierarchical memory modules with iterative refinement.
result V-HMN achieves strong performance on image classification benchmarks.
Forecasting the future traffic flow distribution in an area is an important issue for traffic management in an intelligent transportation system. The key challenge of traffic prediction is to capture spatial and temporal relations between future traffic flows and historical traffic due to highly dynamical patterns of h…
EpiMer merges models by solving Fréchet mean on a Riemannian manifold.
problem Integrating knowledge from multiple models without retraining.
method EpiMer casts model merging as solving the Fréchet mean on a Riemannian manifold, restricting computation to a low-rank subspace.
result EpiMer outperforms flat-geometry methods on image classification tasks.
Proteins are the major building blocks of life, and actuators of almost all chemical and biophysical events in living organisms. Their native structures in turn enable their biological functions which have a fundamental role in drug design. This motivates predicting the structure of a protein from its sequence of amino…
Paper tackles fairness issues in GNNs by proposing ELEGANT for certification.
problem Fairness issues in GNN predictions due to graph data perturbations.
method Proposes ELEGANT framework for certifying fairness of any GNN without assumptions or re-training.
result The fairness of any GNN backbone is impossible to be corrupted under certain perturbation budgets.
An analysis of the Japanese credit market in 2004 between banks and quoted firms is done in this paper using the tools of the networks theory. It can be pointed out that: (i) a backbone of the credit channel emerges, where some links play a crucial role; (ii) big banks privilege long-term contracts; the "minimal spanni…
Self-supervised method improves representation learning for better accuracy.
problem Improving representation learning without manual annotation.
method Proposes a novel self-supervised formulation of relational reasoning.
result Self-supervised relational reasoning outperforms state-of-the-art models by 14% in accuracy.
SPIRE enables efficient federated learning for diffusion models by separating client-specific embeddings from a shared backbone.
problem Large diffusion models are impractical for federated learning due to their size.
method SPIRE separates the network into a global backbone and client-specific embeddings, enabling efficient finetuning.
result SPIRE achieves parameter-efficient finetuning, updating only a small fraction of weights.
Paper proposes a method to improve MCMC sampling for energy-based models.
problem MCMC sampling of energy-based models is often not mixing in high-dimensional data.
method Proposes using a flow-based model as a backbone to correct the energy-based model, enabling mixing in latent space.
result MCMC sampling of the corrected EBM in the latent space mixes well and traverses modes in the data space.
LDA improves image classification accuracy with fewer features.
problem Fine-grained image classification with pretrained features.
method Supervised dimensionality reduction with LDA before linear probing.
result LDA improves accuracy over full features in 11 out of 12 configurations.
A new OOD detection method OTOD uses optimal transport theory to improve model performance.
problem Detecting unknown samples in real-world machine learning models.
method OTOD uses optimal transport theory to calculate an OOD score combining features, logits, and softmax probability space.
result OTOD outperforms state-of-the-art methods by significant margins on benchmarks.
The backbone of most proteins forms an open curve. To study their entanglement, a common strategy consists in searching for the presence of knots in their backbones using topological invariants. However, this approach requires to close the curve into a loop, which alters the geometry of curve. Knoto-ID allows evaluatin…
Dropout improves MIL performance on noisy WSI classification.
problem Noisy feature embeddings and weak supervision in MIL for WSI classification.
method Empirical exploration of dropout in MIL, proposing MIL-Dropout.
result MIL-Dropout boosts MIL performance with minimal computational cost.
A chord diagram consists of a circle, called the backbone, with line segments, called chords, whose endpoints are attached to distinct points on the circle. The genus of a chord diagram is the genus of the orientable surface obtained by thickening the backbone to an annulus and attaching bands to the inner boundary cir…
SIGNNAP learns stable and identifiable node representations in GNNs against graph perturbations.
problem Fragility of GNN models to graph perturbations leading to unreliable node representations.
method SIGNNAP proposes a novel model that learns stable and identifiable node representations in an unsupervised manner, formalizing stability and identifiability through a contrastive objective and preserving smoothness with existing GNN backbones.
result SIGNNAP demonstrates effectiveness in learning stable and identifiable node representations in GNNs against graph perturbations on six benchmarks.
Extends geostatistical simulation method to handle multiple variables and large grids.
problem Scalability and handling of multiple variables in geostatistical simulation.
method Uses Sinkhorn optimal transport with sparse matcher and FFT-MA Gaussian backbone.
result MST-Direct reproduces joint distribution with zero histogram error and accurately preserves spatial correlation.
Time-related features improve time series forecasting models.
problem Lack of explicit time-related encoding in current forecasting models limits their ability to capture cyclical and seasonal trends.
method Introducing Time Stamp Forecaster (TimeSter) to encode time-related features and integrating it with a linear backbone.
result TimeLinear model reduces MSE by 23% on benchmark datasets, improving performance with exceptional efficiency.
A new algorithm reduces communication in graph-structured VFL.
problem Training GNNs in VFL with interrelated samples.
method Model splitting and lazy aggregation.
result GLASU trains GNNs with reduced communication, matching centralized performance.
ProtoryNet interprets text sequences using prototype trajectories for better understanding.
problem Improving text classification interpretability and accuracy.
method ProtoryNet uses prototype trajectories to interpret text sequences, with prototype pruning for better interpretability.
result ProtoryNet outperforms baseline models and reduces performance gap compared to black-box models.
AugMask trains diffusion models on incomplete tabular data by augmenting missing values and applying denoising supervision.
problem Training diffusion models on incomplete tabular data with missing values.
method AugMask uses stochastic augmentation and denoising supervision to adapt diffusion models to incomplete data.
result AugMask enables diffusion-based tabular generators to outperform specialized missing-aware baselines across various datasets and missingness regimes.
Efficiently generates high-resolution images with reduced sampling time using LEGO bricks.
problem Efficiently generating high-resolution images with reduced sampling time.
method Introduces LEGO bricks that integrate Local-feature Enrichment and Global-content Orchestration to create a test-time reconfigurable diffusion backbone.
result Significantly reduces sampling time compared to other methods.
Study local commutation relation on almost complex manifolds.
problem Local commutation relation between Lefschetz operator and exterior differential.
method Analyzing almost complex manifolds with compatible metrics.
result Generalizes local Kähler identities to almost Hermitian manifolds.
We present a methodology to extract the backbone of complex networks based on the weight and direction of links, as well as on nontopological properties of nodes. We show how the methodology can be applied in general to networks in which mass or energy is flowing along the links. In particular, the procedure enables us…
We present MLRG Deep Curvature suite, a PyTorch-based, open-source package for analysis and visualisation of neural network curvature and loss landscape. Despite of providing rich information into properties of neural network and useful for a various designed tasks, curvature information is still not made sufficient us…
Geometric theory of projection heads in self-supervised learning.
problem Dimensional collapse and information invariance trade-off in projection heads.
method Geometric modeling of projection heads as Riemannian metrics, analyzing Hessian eigenvalues, and tracking optimization geometry.
result Smooth nonlinear heads induce negative curvature, preventing collapse; linear and ReLU heads cannot.
Extracts causal brain dynamics across multiple scales.
problem Statistical associations do not reflect causal mechanisms in brain dynamics.
method Multiscale causal backbone (MCB) extraction using advanced causal structure learning.
result Sparse MCBs reveal distinct causal roles at different brain frequency bands.
EPFGNN models graph connections for better node classification.
problem Graph node classification issues due to feature aggregation.
method EPFGNN models graph as a Markov Random Field with explicit pairwise factors and a GNN backbone.
result EPFGNN improves semi-supervised node classification performance.
SurvFM-RMST converts survival outcomes into pseudo-observation targets for tabular models.
problem Right-censored follow-up prevents direct use of survival labels in tabular patient data.
method SurvFM-RMST framework that converts survival outcomes into jackknife pseudo-observation targets for restricted mean survival time.
result SurvFM-RMST accurately recovered restricted event-free time in simulations and outperformed naive targets in static datasets.
We show that the Khovanov complex of a rational tangle has a very simple representative whose backbone of non-zero morphisms forms a zig-zag. Furthermore, this minimal complex can be computed quickly by an inductive algorithm. (For example, we calculate Kh(82) by hand.) We find that the bigradings of the subobjects …