ISI-CV derives a synaptic importance score from the regularity of neuron firing intervals to enable continual learning without gradients or forgetting on SNNs.
super hub Baseline reference
Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
Baseline reference. 65% of citing Pith papers use this work as a benchmark or comparison.
240
Pith papers citing it
6,091
external citations · Pith
Baseline
65% of classified citations
abstract
We present Fashion-MNIST, a new dataset comprising of 28x28 grayscale images of 70,000 fashion products from 10 categories, with 7,000 images per category. The training set has 60,000 images and the test set has 10,000 images. Fashion-MNIST is intended to serve as a direct drop-in replacement for the original MNIST dataset for benchmarking machine learning algorithms, as it shares the same image size, data format and the structure of training and testing splits. The dataset is freely available at https://github.com/zalandoresearch/fashion-mnist
hub tools
citation-role summary
dataset 13
background 7
citation-polarity summary
claims ledger
- abstract We present Fashion-MNIST, a new dataset comprising of 28x28 grayscale images of 70,000 fashion products from 10 categories, with 7,000 images per category. The training set has 60,000 images and the test set has 10,000 images. Fashion-MNIST is intended to serve as a direct drop-in replacement for the original MNIST dataset for benchmarking machine learning algorithms, as it shares the same image size, data format and the structure of training and testing splits. The dataset is freely available at https://github.com/zalandoresearch/fashion-mnist
authors
co-cited works
representative citing papers
A hybrid evolution-strategy and gradient-descent framework maximizes a non-differentiable 'surprise score' to discover non-random features for non-parametric self-supervised image clustering.
Model merging is cast as PoE inference with EBM experts, revealing Gaussian assumptions in prior work and proposing convergent Cauchy experts that improve empirical performance.
Extends solvable GAN theory to structured latent covariances, proving convergence of stochastic training to ODEs and identifying a correlation-based signal-boosting mechanism for subspace recovery.
Direct fixed-weight solver for free-support Wasserstein medians relocates atoms using OT barycentric projections and inverse-distance weights, achieving monotone descent on smoothed objectives with fewer subproblems than nested Weiszfeld baselines.
GrapNet defines a graph-as-architecture neural substrate with node-owned child references and allocation vectors that supports structural edits and shows accuracy gains over MLPs in continual learning on Split Fashion-MNIST and CIFAR-10.
ZOMA unifies hybrid zeroth-order estimators, bias corrections (GT/ED/EXTRA), and accelerations (STORM/PAGE/L2S) for decentralized nonconvex PL minimax optimization, claiming convergence rates matching centralized methods plus linear speedup.
End-to-end phase-mask optimization improves classification under constrained detector readout by increasing class separability but yields no benefit under full readout, where a conventional lens approaches the mutual-information ceiling.
Only the gradient component of score errors affects marginal distributions in diffusion models, so L2 error can be arbitrarily large with perfect match; this yields an impossibility result, a gradient-only KL bound, and a Sobolev estimator that correlates better with quality.
CtM merges T LoRAs into one rank-r LoRA by computing shared r-dimensional subspaces from the LoRA weights, projecting adapters into r x r coordinates, and merging in that reduced space, outperforming merge-then-compress baselines in experiments.
PC-ALM uses dual ascent on an augmented Lagrangian to achieve exact backpropagation gradients via layer-local updates in linear networks and matching performance in nonlinear networks up to depth 128.
A neural network is trained to predict parameters of a fixed quantum circuit, enabling high-fidelity quantum state preparation from classical data in one inference step with up to 0.992 fidelity on unseen MNIST and Fashion-MNIST images.
ScaleMAP is a dimensionality-reduction method that preserves both neighborhood structure and local density by scaling embedding displacements with original local radii, matching DensMAP on density while retaining UMAP-level neighborhood fidelity.
Introduces complement-aware submodular functions (CSI) that preserve structure between subset and complement for improved robust data selection.
Class-split anomaly detection benchmarks can yield collapsing or inverted anomaly scores when the held-out class overlaps normal data in representation space, with neighborhood class leakage predicting this instability across image datasets.
Proposes pointwise Riemannian Dimension from feature eigenvalues to derive tighter, representation-aware generalization bounds for deep networks in the nonlinear regime.
BESplit mitigates non-IID bias in split federated learning via evidential aggregation, bias-compensated client pairing, and dual-teacher distillation, outperforming prior methods on five benchmarks.
PCDM uses a poisoning-oriented conditional diffusion model with an adjustable vector and jumping strategy to create stealthier and more effective poisoned data than GAN-based attacks against federated learning.
QUBO formulation on quantum annealers for joint client selection in federated learning, combined with a MultiSignal routing ensemble, yields higher Byzantine attack detection accuracy than MultiKrum on challenging attacks at both small and moderate scales.
A framework combining VQ-VAE, task-relevance scoring, DRL subset selection, and a learned semantic-aware constellation claims near-100% semantic protection probability and proves standard Gray-coded constellations are suboptimal under non-uniform importance.
QLL is a novel logic for neuro-symbolic learning that uses ML-native operations (sum, log-sum-exp) on logits to embed constraints, satisfying most linear logic properties and showing stronger correlation between empirical robustness and formal verification than prior approaches.
QLAM extends state-space models with quantum superposition in the hidden state for linear-time long-sequence modeling and reports consistent gains over RNN and transformer baselines on sequential image tasks.
FeatCal reduces feature drift in merged models via layer-wise closed-form calibration on a small dataset, outperforming prior post-merging methods on CLIP and GLUE benchmarks with high sample efficiency.
SubPopMark embeds verifiable subpopulation biases into distilled datasets via CVM and USTM optimization stages, allowing provenance inference through comparison of model output signatures against a reference behavior bank.
citing papers explorer
-
Gradient-Free Continual Learning in Spiking Neural Networks via Inter-Spike Interval Regularization
ISI-CV derives a synaptic importance score from the regularity of neuron firing intervals to enable continual learning without gradients or forgetting on SNNs.
-
Converge to Surprise: Evolutionary Self-supervised Image Clustering
A hybrid evolution-strategy and gradient-descent framework maximizes a non-differentiable 'surprise score' to discover non-random features for non-parametric self-supervised image clustering.
-
Model Merging as Probabilistic Inference in Fine-Tuning Parameter Space
Model merging is cast as PoE inference with EBM experts, revealing Gaussian assumptions in prior work and proposing convergent Cauchy experts that improve empirical performance.
-
Effective Covariance Dynamics in Solvable High-Dimensional GANs
Extends solvable GAN theory to structured latent covariances, proving convergence of stochastic training to ODEs and identifying a correlation-based signal-boosting mechanism for subspace recovery.
-
Fast Computation of Free-Support Wasserstein Medians
Direct fixed-weight solver for free-support Wasserstein medians relocates atoms using OT barycentric projections and inverse-distance weights, achieving monotone descent on smoothed objectives with fewer subproblems than nested Weiszfeld baselines.
-
GrapNet: A Programmable Dynamic-Architecture Neural Graph Substrate
GrapNet defines a graph-as-architecture neural substrate with node-owned child references and allocation vectors that supports structural edits and shows accuracy gains over MLPs in continual learning on Split Fashion-MNIST and CIFAR-10.
-
A Unified Zeroth-Order Approach for Decentralized Minimax Optimization
ZOMA unifies hybrid zeroth-order estimators, bias corrections (GT/ED/EXTRA), and accelerations (STORM/PAGE/L2S) for decentralized nonconvex PL minimax optimization, claiming convergence rates matching centralized methods plus linear speedup.
-
End-to-End Optimization of Incoherent Imaging for Classification Under Detector-Limited Readout
End-to-end phase-mask optimization improves classification under constrained detector readout by increasing class separability but yields no benefit under full readout, where a conventional lens approaches the mutual-information ceiling.
-
Diffusion Models Observe Only Gradients: A Geometric Perspective on Score Matching Errors
Only the gradient component of score errors affects marginal distributions in diffusion models, so L2 error can be arbitrarily large with perfect match; this yields an impossibility result, a gradient-only KL bound, and a Sobolev estimator that correlates better with quality.
-
Compress then Merge: From Multiple LoRAs into One Low-Rank Adapter
CtM merges T LoRAs into one rank-r LoRA by computing shared r-dimensional subspaces from the LoRA weights, projecting adapters into r x r coordinates, and merging in that reduced space, outperforming merge-then-compress baselines in experiments.
-
Augmented Lagrangian Predictive Coding
PC-ALM uses dual ascent on an augmented Lagrangian to achieve exact backpropagation gradients via layer-local updates in linear networks and matching performance in nonlinear networks up to depth 128.
-
Quantum State Preparation via Neural Network Encoding in Quantum Machine Learning
A neural network is trained to predict parameters of a fixed quantum circuit, enabling high-fidelity quantum state preparation from classical data in one inference step with up to 0.992 fidelity on unseen MNIST and Fashion-MNIST images.
-
ScaleMAP: Preserving Local Density and Neighborhood Structure in Low-Dimensional Embeddings
ScaleMAP is a dimensionality-reduction method that preserves both neighborhood structure and local density by scaling embedding displacements with original local radii, matching DensMAP on density while retaining UMAP-level neighborhood fidelity.
-
Complement Submodular Information Measures for Balanced and Robust Data Selection
Introduces complement-aware submodular functions (CSI) that preserve structure between subset and complement for improved robust data selection.
-
Testing the Test: Score-Direction Instability in Class-Split Anomaly Detection
Class-split anomaly detection benchmarks can yield collapsing or inverted anomaly scores when the held-out class overlaps normal data in representation space, with neighborhood class leakage predicting this instability across image datasets.
-
Pointwise Generalization in Deep Neural Networks
Proposes pointwise Riemannian Dimension from feature eigenvalues to derive tighter, representation-aware generalization bounds for deep networks in the nonlinear regime.
-
BESplit: Bias-Compensated Split Federated Learning with Evidential Aggregation
BESplit mitigates non-IID bias in split federated learning via evidential aggregation, bias-compensated client pairing, and dual-teacher distillation, outperforming prior methods on five benchmarks.
-
PCDM: A Diffusion-Based Data Poisoning Attack Against Federated Learning Systems
PCDM uses a poisoning-oriented conditional diffusion model with an adjustable vector and jumping strategy to create stealthier and more effective poisoned data than GAN-based attacks against federated learning.
-
Byzantine-Resilient Federated Learning via QUBO-Based Client Selection on Quantum Annealers
QUBO formulation on quantum annealers for joint client selection in federated learning, combined with a MultiSignal routing ensemble, yields higher Byzantine attack detection accuracy than MultiKrum on challenging attacks at both small and moderate scales.
-
Not All Symbols Are Equal: Importance-Aware Constellation Design for Semantic Communication
A framework combining VQ-VAE, task-relevance scoring, DRL subset selection, and a learned semantic-aware constellation claims near-100% semantic protection probability and proves standard Gray-coded constellations are suboptimal under non-uniform importance.
-
Quantitative Linear Logic for Neuro-Symbolic Learning and Verification
QLL is a novel logic for neuro-symbolic learning that uses ML-native operations (sum, log-sum-exp) on logits to embed constraints, satisfying most linear logic properties and showing stronger correlation between empirical robustness and formal verification than prior approaches.
-
QLAM: A Quantum Long-Attention Memory Approach to Long-Sequence Token Modeling
QLAM extends state-space models with quantum superposition in the hidden state for linear-time long-sequence modeling and reports consistent gains over RNN and transformer baselines on sequential image tasks.
-
FeatCal: Feature Calibration for Post-Merging Models
FeatCal reduces feature drift in merged models via layer-wise closed-form calibration on a small dataset, outperforming prior post-merging methods on CLIP and GLUE benchmarks with high sample efficiency.
-
From Compression to Accountability: Harmless Copyright Protection for Dataset Distillation
SubPopMark embeds verifiable subpopulation biases into distilled datasets via CVM and USTM optimization stages, allowing provenance inference through comparison of model output signatures against a reference behavior bank.
-
Implicit Neural Optimal Transport via Fixed-Point Optimization
A single-network implicit neural optimal transport method that solves the c-transform via proximal fixed-point iteration for stable, non-adversarial training.
-
Classification-Head Bias in Class-Level Machine Unlearning: Diagnosis, Mitigation, and Evaluation
Class-level unlearning shortcuts via bias suppression in the classification head; new bias-aware training mechanisms and bias-specific metrics are introduced to diagnose and reduce this dependence.
-
Pre-training Enables Extraordinary All-optical Image Denoising
Pre-training diffractive optical networks on millions of simple images followed by fine-tuning enables all-optical denoising that raises PSNR from below 8 dB to above 18 dB across diverse datasets including MNIST, ChestMNIST, CIFAR-10 and CelebA.
-
TRACE: Transport Alignment Conformal Prediction via Diffusion and Flow Matching Models
TRACE creates valid conformal prediction sets for complex generative models by scoring outputs via averaged denoising or velocity errors along stochastic transport paths instead of likelihoods.
-
Test-Time Compositional Generalization in Diffusion Models via Concept Discovery
Diffusion models can extract reusable density-mode concepts from their time-indexed scores to enable compositional generation at test time on held-out benchmarks from ColorMNIST and CelebA.
-
The Interplay of Data Structure and Imbalance in the Learning Dynamics of Diffusion Models
Higher-variance classes are learned first in diffusion models; strong class imbalance reverses the order and imposes distinct delayed learning times on minority classes.
-
Non-Myopic Active Feature Acquisition via Pathwise Policy Gradients
NM-PPG optimizes non-myopic acquisition policies for costly features by enabling pathwise gradients via continuous relaxation and straight-through rollouts in POMDPs, outperforming SOTA baselines.
-
Spectral Graph Sparsification Preserves Representation Geometry in Graph Neural Networks
Spectral sparsification preserves GNN embedding geometry up to O(ε) perturbations in filters, representations, Gram matrices, and training trajectories.
-
Quantum Interval Bound Propagation for Certified Training of Quantum Neural Networks
QIBP adapts interval bound propagation to quantum neural networks for certified adversarial robustness via interval and affine arithmetic implementations.
-
Heterogeneous-Horizon Exact-Weight Local SGD
HEW-Local SGD provides exact-weight adaptive aggregation for heterogeneous local SGD with one-step guarantees and explicit convergence results under unequal local horizons.
-
Diverse Dictionary Learning
Diverse dictionary learning identifies intersections, complements, and dependency structures of latent variables from data X = g(Z) up to indeterminacies, and full identifiability when structural diversity is sufficient.
-
The Multi-Block DC Function Class: Theory, Algorithms, and Applications
The Multi-Block DC class admits polynomial-size DC decompositions for problems that require exponential size under standard DC programming and supplies explicit constructive formulations for deep ReLU networks together with convergent batch and stochastic algorithms.
-
Feature-level analysis and adversarial transfer in rotationally equivariant quantum machine learning
Rotationally equivariant quantum models can rely on vulnerable invariant statistics such as ring-averaged intensities, leaving them susceptible to classical transfer attacks, but suppressing the associated symmetry sectors substantially improves robustness.
-
The Linear Centroids Hypothesis: Features as Directions Learned by Local Experts
The Linear Centroids Hypothesis reframes network features as directions in centroid spaces of local affine experts, unifying interpretability methods and yielding sparser, more faithful dictionaries, circuits, and saliency maps.
-
Tensor-based Multi-layer Decoupling
A new tensor framework for multi-layer decoupling of multivariate functions is proposed via ParaTuck decompositions and bilevel optimization.
-
Toward Exact Convergence in Byzantine-Robust Decentralized Learning: A Statistical Identification Approach
DRSGD-ByMI identifies Byzantine machines via sample-splitting score statistics with FDR control, then prunes them to recover sufficient connectivity and achieve order-optimal convergence rates identical to standard decentralized SGD.
-
XFED: Non-Collusive Model Poisoning Attack Against Byzantine-Robust Federated Classifiers
XFED is the first aggregation-agnostic non-collusive model poisoning attack that bypasses eight state-of-the-art defenses on six benchmark datasets without attacker coordination.
-
Instance-Adaptive Parametrization for Amortized Variational Inference
IA-VAE augments amortized variational inference with hypernetwork-generated instance-adaptive modulations, strictly containing the standard variational family and improving held-out ELBO on synthetic and image data.
-
Selectivity and Shape in the Design of Forward-Forward Goodness Functions
Shape- and peak-sensitive goodness functions for Forward-Forward deliver up to 72pp gains over sum-of-squares, reaching 98.2% on MNIST and 89% on Fashion-MNIST.
-
How Out-of-Equilibrium Phase Transitions can Seed Pattern Formation in Trained Diffusion Models
Pattern formation in trained diffusion models emerges from out-of-equilibrium phase transitions driven by instabilities in low-frequency denoising modes linked to data symmetries and architectural constraints.
-
Programmable superconducting neuron with intrinsic in-memory computation and dual-timescale plasticity for ultra-efficient neuromorphic computing
A programmable superconducting LIF neuron with intrinsic static memory and dual-timescale plasticity achieves 45 GHz operation and femtojoule energy per spike.
-
FlashSinkhorn: IO-Aware Entropic Optimal Transport on GPU
FlashSinkhorn delivers up to 32x forward and 161x end-to-end speedups for entropic OT on A100 GPUs via IO-aware Triton kernels that fuse log-domain updates and streaming transport application.
-
Re-Key-Free, Risky-Free: Adaptable Model Usage Control
AdaLoc keeps a model locked to authorized users by confining all post-deployment updates to a chosen subset of weights, preserving both task performance for authorized use and near-random accuracy for unauthorized use across vision and language models.
-
Tensor Computation of Euler Characteristic Functions and Transforms
A GPU-optimized tensor method computes WECT and ECF for arbitrary-dimensional simplicial and cubical complexes with reported speedups over prior approaches and ships as the pyECT Python package.
-
RACE Attention: A Strictly Linear-Time Attention Layer for Training on Outrageously Large Contexts
RACE Attention is a strictly linear-time attention mechanism that approximates softmax attention outputs using Gaussian projections and soft LSH to enable training on contexts up to 12 million tokens.
-
The Tsetlin Machine Goes Deep: Logical Learning and Reasoning With Graphs
GraphTM uses message passing on graphs to build nested deep clauses, achieving 3.86% higher accuracy than convolutional TM on CIFAR-10 and competitive results on action tracking, recommendations, and genome sequences.