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.
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.
New similarity index avoids limitations of CCA in neural networks.
problem Limitations of existing methods in measuring neural network representation similarity.
method Introducing a similarity index based on centered kernel alignment (CKA) to measure representational similarity matrices.
result CKA reliably identifies correspondences between representations in networks trained from different initializations.
Neural networks auto-denoise similar inputs, enabling new statistical analysis.
problem Estimating similarity of inputs for neural networks.
method Define and quantify similarity from neural network perspective, using parameter variation impact on outputs.
result Estimate sample density and quantify denoising effect without true labels.
Detects change-points in similarity networks to identify anomalous nodes.
problem Detecting changes in network structure that affect node similarity.
method Sequential node-wise average similarity measures for change detection; community detection for anomaly isolation.
result Simple sequential procedure effectively identifies change-points and anomalous nodes.
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.
Study reveals similarity between GAN generator and discriminator networks.
problem Understanding the structure and similarity of GAN networks.
method Examined the weights and structure of GAN networks, focusing on generator and discriminator similarities.
result Both GAN generator and discriminator networks have a similar structure, as evidenced by experimental results.
The paper analyzes the generalization of deep neural networks for metric and similarity learning.
problem Lack of rigorous understanding of generalization performance in metric and similarity learning.
method Derive explicit form of true metric, construct structured deep ReLU neural network, establish excess risk bounds.
result Explicit excess risk bounds for metric and similarity learning are derived.
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.
Unified deep network learns shared representation and cross-media similarity metric for multimedia data.
problem Improving cross-media retrieval by capturing complex correlations among multiple media types.
method Unified Network for Cross-media Similarity Metric (UNCSM) that combines shared representation learning and distance metric calculation.
result UNCSM outperforms state-of-the-art methods on 4 cross-media datasets.
Different neural networks learn similar mappings with different weights.
problem Understanding shared representations across neural networks with varying weights.
method Shared response model and orthogonal transformations.
result Different neural networks encode the same input examples as different orthogonal transformations of an underlying shared representation.
Researchers compare brain connectomes using geodesic distance on manifold for twin pairs.
problem Assessing functional similarity in brain networks between monozygotic and dizygotic twins.
method Using fMRI data, the researchers compared functional networks between mono- and dizygotic twin pairs by measuring similarity with geodesic distance on graph Laplacians.
result Functional networks are more similar in monozygotic twins compared to dizygotic twins, and similarity is higher for task-relevant networks.
GSimCNN predicts graph similarity using CNNs, outperforming existing methods.
problem Challenging pairwise graph similarity computation due to NP-hardness.
method Graph Edit Distance (GED) as core metric, GSimCNN (Convolutional Neural Networks).
result State-of-the-art performance on graph similarity search.
Proposes a new neural network approach to credit assignment.
problem Credit assignment problem in deep neural networks.
method Contrastive similarity matching objective function.
result Deep networks learn to match similarity between layers.
WIPS optimizes inner product weights to approximate various similarities.
problem Learning high-quality node representations and accurate similarities.
method Weighted inner product similarity (WIPS) with adjustable weights.
result WIPS can approximate arbitrary general similarities including positive definite and indefinite kernels.
Graph Matching Networks learn graph similarity using GNN embeddings.
problem Learning similarity between graph structured objects.
method Graph Matching Network model using cross-graph attention mechanism.
result Models outperform baseline systems in function similarity search.
Quantum networks learn task-dependent asymmetric similarity measures.
problem Challenges of conventional distance functions in capturing meaningful similarity.
method GQSim: Quantum networks for learning task-dependent (a)symmetric similarity.
result Quantum similarity measures extract salient features and achieve theoretically guaranteed performance.
Proposes neural similarity for CNNs to enhance flexibility and performance.
problem Limited flexibility of inner product-based convolution in CNNs.
method Introduces neural similarity as a learnable parametric similarity measure, and proposes NSL for adaptive learning from data.
result Dynamic neural similarity improves flexibility and performance in visual recognition and few-shot learning.
Proposes a new similarity learning framework for brain networks.
problem Learning similarity metrics for neuroimages, especially fMRI and DTI.
method End-to-end similarity learning framework using Higher-order Siamese GCN.
result Achieves significant AUC gains over existing methods.
hood2vec identifies urban area similarity via mobility networks.
problem Identifying similar urban areas using mobility networks.
method Learning node embeddings of the mobility network from Foursquare check-ins.
result Mobility dynamics capture different aspects of urban area similarity than venue types.
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.
SimGNN uses neural networks to quickly find similar graphs.
problem Efficiently computing graph similarity, especially for large graphs.
method Embedding function + attention mechanism + pairwise node comparison.
result SimGNN achieves better performance and faster computation than existing methods.
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.
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.
Graph neural networks improve with edge similarity constraints in RNA structure analysis.
problem Lack of edge similarity constraints in graph neural networks.
method Introduced a graph neural network layer that leverages prior information about edge similarities.
result Edge similarity constraints do not enhance performance in graph neural networks.
Investigation of the market graph attracts a growing attention in market network analysis. One of the important problem connected with market graph is to identify it from observations. Traditional way for the market graph identification is to use a simple procedure based on statistical estimations of Pearson correlatio…
Cosine normalization uses cosine similarity to reduce neuron variance in neural networks.
problem Large variance in neuron outputs leads to poor generalization and internal covariate shift.
method Replace dot product with cosine similarity or centered cosine similarity in neural networks.
result Cosine normalization improves model performance on various datasets.
Proposes a regularization method for Bayesian networks to improve model generalization.
problem Improving model generalization in Bayesian networks.
method Distribution-based penalization approach that encourages similar conditional probability distributions.
result Proposed method solves the wave propagation modeling problem better than baseline methods.
Improved CNN for HCCR with new loss function and ranking method.
problem Loss of inter-class information in traditional CNN models for HCCR.
method Combining cross entropy with a new similarity ranking function (Average variance similarity) as loss function.
result New loss function (SoftMax cross entropy with Average variance similarity) achieves highest accuracy in HCCR.
A new method identifies similar mutual funds using graph learning.
problem Identifying similar mutual funds with nuanced portfolio similarities.
method Node2Vec machine learning method applied to a weighted bipartite network of funds and assets.
result Identifies structural similarity among mutual funds' portfolios.
A new neural network model extends word embedding vectors with MeSH concepts for biomedical semantic similarity.
problem Eliciting semantic similarity between biomedical concepts remains challenging.
method Proposes a MeSH-gram neural network model that extends skip-gram by using MeSH descriptors.
result MeSH-gram outperforms skip-gram and is comparable to best methods but requires more computation and external resources.
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.
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.
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.
CNEs improve network embeddings by adding structural information.
problem Hard embedding of certain networks due to structural properties.
method Bayesian approach to create embeddings that maximize information with given structural properties.
result CNEs outperform state-of-the-art methods in link prediction and multi-label classification.
A new model SIPS improves graph embedding by approximating non-PD similarities.
problem Improving neural network-based graph embedding by approximating non-positive definite similarities.
method Shifted Inner Product Similarity (SIPS) model that approximates Conditionally Positive Definite (CPD) similarities.
result SIPS significantly improves graph embedding without configuring the similarity function.
Framework for inferring latent structure from sparse, imperfectly detected bipartite networks.
problem Recovering latent structure from sparse, imperfectly detected bipartite networks in ecology.
method Structured sparse nonnegative low-rank factorization with detection probability estimation and ADMM-based algorithm.
result Improved recovery of latent factors and structure compared to existing methods.
SIPS extends graph embedding by approximating more types of similarities.
problem Graph embedding's limitation in approximating certain types of similarities.
method Shifted inner-product similarity (SIPS) with bias terms.
result SIPS can approximate PD and CPD similarities, improving graph embedding performance.
Paper tests similarity between networks using a bootstrap method.
problem Determining if two networks are similar or proportional.
method Parametric bootstrap approach and Frobenius norm-based test.
result The method is versatile and consistent under various models.
TLMG4Eth combines language and graph models for Ethereum fraud detection.
problem Current fraud detection methods fail to consider semantic and similarity patterns in Ethereum transactions.
method TLMG4Eth uses a transaction language model and graph-based methods to capture semantic, similarity, and structural features.
result TLMG4Eth detects anomalies in Ethereum transactions more effectively than existing methods.
Graph change-point detection method learns graph similarity from data.
problem Detect abrupt changes in dynamic networks.
method Siamese graph neural network for graph similarity learning.
result Method detects changes in diverse types of networks with minimal data history.
NeuralWarp aligns time-series indices using deep learning for improved similarity.
problem Need for elastic time-series similarity measures.
method Proposes NeuralWarp, a deep learning model for aligning time-series indices.
result NeuralWarp outperforms non-parametric and un-warped deep models.
Subspace match fails to accurately assess neural network representations.
problem Understanding the learned representations of neural networks.
method Subspace match method to assess representation similarity.
result Representations with low subspace match can still be isomorphic.
Proposes a simple neural network model similar to gradient boosted decision trees.
problem Building a neural network equivalent to gradient boosted decision trees.
method Converts an ensemble of decision trees to a neural network, relaxes properties, and trains a simple neural network model.
result The proposed Hammock model achieves similar performance to gradient boosted decision trees.
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.
New measure assesses neural network models' functional similarity.
problem Measuring functional similarity between similar-performing neural networks.
method Robust nonparametric hypothesis testing framework.
result Proposed measure assesses neural networks' functional similarity.
Adapts auxiliary losses using gradient similarity to improve neural network performance.
problem Statistical inefficiency in neural networks and difficulty in selecting helpful auxiliary tasks.
method Uses cosine similarity between gradients of tasks to adaptively weight auxiliary losses.
result Guaranteed convergence to critical points of the main task and practical usefulness across domains.
Paper proposes LSTM for speaker similarity measurement and improves diarization accuracy.
problem Improving speaker diarization accuracy using neural networks.
method Uses Bi-LSTM for similarity measurement and spectral clustering for clustering.
result Significantly outperforms state-of-the-art methods with diarization error rate of 6.63%.