Research
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.

168,742 papers · 148 categories

Trend · papers per month

235470705940 · Jun 202019922001200920172026
48 results for Neural similarity

Method measures weight similarity in neural networks using normalization and statistical inference.

problem Quantifying weight similarity in non-convex neural networks.
method Chain normalization rule and hypothesis-training-testing statistical inference.
result Weights of identical neural networks converge to similar local solutions.

Inner product-based convolution has been the founding stone of convolutional neural networks (CNNs), enabling end-to-end learning of visual representation. By generalizing inner product with a bilinear matrix, we propose the neural similarity which serves as a learnable parametric similarity measure for CNNs. Neural si…

2019-10-28abs ↗pdf ↗

Deconfounds neural network representation similarity metrics to improve consistency and accuracy.

problem Confounding by population structure in similarity metrics like RSA and CKA.
method Covariate adjustment regression to adjust for confounders.
result Improves detection of semantically similar neural networks and consistency in transfer learning.

Unified understanding of neural representation similarity measures.

problem Fragmented research landscape of neural network similarity measures.
method Observation and exploration of connections between shape distances and normalized Bures similarity.
result Cosine of the Riemannian shape distance equals normalized Bures similarity.

Improves confidence calibration in neural networks by smoothing labels based on class similarity.

problem Improving confidence calibration in deep neural networks for safety-critical applications.
method Proposes a novel label smoothing technique where label values are based on similarities with the reference class, using different similarity measurements.
result Consistently outperforms state-of-the-art calibration techniques on various datasets and network architectures.

Proposes a method to compare neural networks using feature and gradient vectors.

problem Understanding the behavior of neural networks trained on different datasets.
method Defines a similarity index using feature and gradient vectors, and employs sketching techniques for efficient comparison.
result Demonstrates superior performance in computing similarity of neural networks trained on different datasets.

PSimGNN partitions graphs into subgraphs for efficient graph similarity computation.

problem Efficiently compute graph similarity scores for large graphs.
method Graph partitioning followed by subgraph-level and node-level comparisons using a graph neural network.
result PSimGNN outperforms state-of-the-art methods in graph similarity computation tasks.

Recent work has sought to understand the behavior of neural networks by comparing representations between layers and between different trained models. We examine methods for comparing neural network representations based on canonical correlation analysis (CCA). We show that CCA belongs to a family of statistics for mea…

2019-05-01abs ↗pdf ↗

Study measures impact of data and neural net similarity on transferability in restaurant sales data.

problem Identify indicators for successful transferability of neural nets across different data sets.
method Empirical study on sales data from six restaurants, calculating indicators based on data and neural net similarities.
result Negative correlations between transferability and indicators, allowing better model performance and fewer transfers.

funcGNN uses graph neural networks to estimate program similarity efficiently.

problem Estimating accurate program similarity for software engineering tasks.
method funcGNN trains on labeled CFG pairs to predict GED between unseen programs using effective embedding vectors.
result funcGNN achieves lower error rate (0.00194) and is 23 times faster than traditional methods.

Introduces CHL, a new loss function for continuous similarity learning.

problem Binary similarity learning limitations.
method CHL is a novel loss function that generalizes histogram loss to continuous similarities.
result CHL solves a wider range of tasks including similarity learning, representation learning, and data visualization.

We propose weighted inner product similarity\textit{weighted inner product similarity} (WIPS) for neural network-based graph embedding. In addition to the parameters of neural networks, we optimize the weights of the inner product by allowing positive and negative values. Despite its simplicity, WIPS can approximate arbitrary general similarities in…

2019-02-27abs ↗pdf ↗

MSA compares neural representations' intrinsic geometry for better understanding.

problem Existing similarity measures fail to capture subtle distinctions between neural network solutions.
method Metric similarity analysis (MSA) using Riemannian geometry.
result MSA can disentangle features of neural computations and compare nonlinear dynamics.

Graph similarity search is among the most important graph-based applications, e.g. finding the chemical compounds that are most similar to a query compound. Graph similarity computation, such as Graph Edit Distance (GED) and Maximum Common Subgraph (MCS), is the core operation of graph similarity search and many other …

2018-08-16abs ↗pdf ↗

Neural network for subgraph similarity computation with pruning.

problem Computing subgraph similarity between a target and query graph.
method Convert pruning to node relabeling, relax to differentiable problem, design neural network for SED computation.
result Establishes new state-of-the-art results across multiple benchmark datasets.

New measures link neural representation geometry to decoding ability.

problem Understanding how neural representations relate to decoding ability.
method Showed that popular similarity measures can be interpreted from a decoding perspective.
result Proved that measures like CKA and CCA quantify alignment between optimal linear readouts.

The study analyzes neural network predictions of knot invariants and finds that braid representations work best.

problem Understanding and predicting knot invariants using neural networks.
method Investigated different knot representations and invariants, proposed a cosine similarity score.
result Braid representations are best for predicting knot invariants, and some invariants are easier to learn than others.

We introduce GSimCNN (Graph Similarity Computation via Convolutional Neural Networks) for predicting the similarity score between two graphs. As the core operation of graph similarity search, pairwise graph similarity computation is a challenging problem due to the NP-hard nature of computing many graph distance/simila…

2018-10-23abs ↗pdf ↗

New framework monitors neural network training and reveals regularisation mechanisms.

problem Overfitting in neural networks and the need for explicit regularizers.
method Model Gradient Similarity (MGS) framework to measure and monitor regularisation.
result Explicit regularizers increase Model Gradient Similarity (MGS).

Partial fusion combines neural networks to balance accuracy and efficiency.

problem Balancing accuracy and computational cost in neural networks.
method Extending weight aggregation methods based on neuron-level similarity, using partial optimal transport to match similar neurons.
result Achieves a flexible tradeoff between computational cost and performance.

Different neural networks trained on the same dataset often learn similar input-output mappings with very different weights. Is there some correspondence between these neural network solutions? For linear networks, it has been shown that different instances of the same network architecture encode the same representatio…

2018-11-28abs ↗pdf ↗

Task loss matching misrepresents similarity between neural network layers.

problem Measuring similarity between neural network layers using task loss matching.
method Task loss matching vs. direct matching; comparison with CCA and CKA.
result Direct matching provides a better similarity index than task loss matching.

Neural network learns kernel functions for survival analysis and prediction intervals.

problem Predicting survival times for individuals based on similar training subjects.
method Develops a neural network framework to learn kernel functions for kernel survival analysis and uses these to construct valid prediction intervals.
result Neural network survival estimators are competitive with existing methods and provide valid prediction intervals.

New findings clarify the link between distributional closeness and representational similarity.

problem When and why do different neural network representations become similar?
method Identifiability theory, focusing on model families including autoregressive language models.
result Small Kullback-Leibler divergence does not guarantee similar representations.

Geometric stability measures neural network robustness, distinguishing from similarity metrics.

problem Lack of robustness in neural network representations.
method Introduces geometric stability, quantified by Shesha metric measuring self-consistency.
result Stability and similarity are uncorrelated, revealing distinct properties of neural network robustness.

Recently, graph neural networks have been adopted in a wide variety of applications ranging from relational representations to modeling irregular data domains such as point clouds and social graphs. However, the space of graph neural network architectures remains highly fragmented impeding the development of optimized …

2018-11-17abs ↗pdf ↗

Eliciting semantic similarity between concepts in the biomedical domain remains a challenging task. Recent approaches founded on embedding vectors have gained in popularity as they risen to efficiently capture semantic relationships The underlying idea is that two words that have close meaning gather similar contexts. …

2018-11-28abs ↗pdf ↗

The paper studies how neural networks evolve representations, finding a unique fixed point for nonlinear activations.

problem Understanding how neural networks transform input data across layers.
method Theoretical framework for the evolution of the kernel sequence, using mean-field regime and Hermite polynomials.
result For nonlinear activations, the kernel sequence converges globally to a unique fixed point.

Matrix factorization is at the heart of many machine learning algorithms, for example, dimensionality reduction (e.g. kernel PCA) or recommender systems relying on collaborative filtering. Understanding a singular value decomposition (SVD) of a matrix as a neural network optimization problem enables us to decompose lar…

2017-02-06abs ↗pdf ↗

Modified RV-coefficient reveals how training affects neural network representations.

problem Understanding how training affects intermediate representations in convolutional neural networks.
method Experimented with modified RV-coefficient (RV2) to compare activation patterns in deep networks trained on varying amounts of data and layers.
result RV2 successfully recovered expected similarity patterns and provided interpretable similarity matrices.

Machine learning improves invoice matching speed and accuracy.

problem Efficiently matching similar invoices from various businesses and organizations.
method Combining machine learning with string similarity functions on invoice datasets.
result Neural network and boosted decision tree outperformed existing solutions.

Enhances graph neural networks by considering feature similarities in node aggregation.

problem Ignoring node feature similarities in traditional graph aggregation schemes.
method Interprets node aggregation as kernel weighting, proposing a framework that considers feature similarities.
result Proposed framework outperforms traditional GCNs in real-world applications.

Unified approach for neural networks with multi-compartmental neurons and non-Hebbian plasticity.

problem Limited computational power of existing neural network models for multi-compartmental neurons and non-Hebbian plasticity.
method Unified extension of similarity matching approach to derive neural networks with multi-compartmental neurons and local, non-Hebbian learning rules.
result Unified approach facilitates understanding of multi-compartmental neuronal structures and non-Hebbian plasticity.

In this paper we propose a method to build a neural network that is similar to an ensemble of decision trees. We first illustrate how to convert a learned ensemble of decision trees to a single neural network with one hidden layer and an input transformation. We then relax some properties of this network such as thresh…

2019-10-17abs ↗pdf ↗

New framework to test neural network representation similarity measures.

problem Disagreements among dissimilarity measures in neural networks.
method Statistical testing framework to evaluate measures based on functional behavior.
result Current metrics have different weaknesses; a classical baseline performs surprisingly well.

New metric captures individual neuron tuning across neural networks.

problem Need a metric that respects individual neuron tuning across different neural networks.
method Derived a 'soft' permutation-based metric using optimal transport theory.
result Metric avoids counter-intuitive outcomes and captures geometric insights.