New neural network outperforms existing methods in scene matching.
problem Automated scene matching with high accuracy and low false positives.
method Convolutional hashing using a new loss function and training scheme.
result Significantly higher true positive rate and 100-fold reduction in false positives.
The paper provides theoretical guarantees for hashing-based neural net compression.
problem Rigorous theoretical guarantees on neural net compression methods.
method Random linear sketching and HashedNets architecture.
result Provable guarantees on the performance of hashing-based neural net compression.
Paper reduces recommender system model size by 90%.
problem Large model size in recommender systems.
method Hybrid frequency and double hashing for model size reduction.
result 90% reduction in model size with no performance loss.
Neural networks encode inputs deterministically and categorically, behaving like hash encoders.
problem Understanding the encoding properties of neural networks.
method Analyzed the input space partitioned by ReLU-like activations in neural networks.
result Neural networks can be represented by unique activation patterns, similar to hash encoders.
GCWSNet improves neural network training speed and accuracy with power transformation.
problem Training deep neural networks efficiently and accurately.
method Developed GCWS for hashing powered-GMM kernel, enabling power transformation on data.
result GCWSNet often improves classification accuracy and converges faster with one epoch.
Framework enhances DNNs against malware attacks.
problem Adversarial malware detection in DNNs.
method Hashing Transformation Deep Neural Networks (HashTran-DNN) with DAE regularizer.
result HashTran-DNN effectively defends against all four known attacks.
The paper develops methods to optimize ranking metrics for hashing.
problem Improving hashing for better retrieval performance.
method Developed tie-aware learning to rank formulations for hashing.
result Established new state-of-the-art for image retrieval by Hamming ranking.
DSHL generates music using segment concatenation and hash learning.
problem Music generation using deep learning.
method Deep recurrent neural network and ranking-based hash learning.
result DSHL generates original and enjoyable music.
ForestHash combines random forests and CNNs for efficient data hashing.
problem Efficiently hashing large datasets while preserving similarity.
method Random forests with light-weight CNNs, grouping classes, and information-theoretic aggregation.
result Significantly outperforms state-of-the-art hashing methods for image retrieval.
A new sketching method reduces tensor memory usage and enables efficient tensor operations.
problem Efficiently compressing and retaining tensor structure in large datasets.
method Higher-order Count Sketch (HCS) using multiple hash functions and tensor products.
result HCS achieves significant memory savings and efficient tensor operations.
New method reduces model size by 75% on ResNet32 without loss in quality.
problem Large models consume too much memory and energy on low-resource devices.
method Structured multi-hashing combining weight hashing and dimensionality reductions.
result Significant reduction in model size with minimal accuracy loss.
A new hashing method handles large-scale data with flexible similarity measures.
problem Efficient nearest neighbour search in large-scale systems with variable labels.
method End-to-end trainable network transforming data to uniform distribution on product of spheres, then hashing to binary form maximizing entropy.
result Outperforms baseline approaches in limited capacity regime.
Efficiently learns quantizable embeddings for fast search.
problem Learning binary hamming code representations for search efficiency.
method Directly learns a quantizable embedding representation and sparse binary hash code end-to-end.
result Achieves state-of-the-art search accuracy and significant speedup.
Fuzzy hashes learn from data to improve file similarity detection.
problem Measuring similarity between files, especially malware.
method Learned fuzzy hashes using a minimax training framework.
result Learned fuzzy hashes outperform traditional methods for file similarity.
Proposes neural decision trees combining neural networks and decision trees.
problem Combining neural networks and decision trees for improved modeling power.
method Integrates multilayer perceptrons into decision tree structure with weight sharing.
result Demonstrates improved modeling power and flexibility over standard decision trees and MLPs.
Paper proposes using LSTM for LSH-based sequence alignment.
problem Sequence alignment using deep learning models.
method Deep bidirectional LSTM for feature learning and LSH-based sequence alignment.
result Higher accuracy achieved with LSTM-based model.
IMSAT learns discrete representations by maximizing information and enforcing invariance.
problem Learning useful discrete representations from data.
method Information Maximizing Self-Augmented Training (IMSAT) with data augmentation and information-theoretic dependency maximization.
result IMSAT achieves state-of-the-art results for clustering and unsupervised hash learning.
Bitcoin mining costs remain stable despite increased activity.
problem Stability of Bitcoin mining costs despite rising energy consumption.
method Estimation of global energy cost over a decade, considering changing oil costs and technological improvements.
result The cost of Bitcoin mining has remained relatively stable since 2010, relative to the volume of transactions.
This study compares neural network compression techniques.
problem Reducing the size of neural networks for limited devices.
method Evaluation of hashing-based, pruning-based, and regularization methods on MNIST and variants.
result Pruning-based methods outperform hashing-based methods, especially at high compression levels.
Sketch-GNN reduces GNN training time and memory usage to sublinear scales.
problem Training GNNs on large graphs is computationally expensive and memory-intensive.
method Develops a sketch-based algorithm that trains GNNs on compact sketches of graph adjacency and node embeddings.
result Training time and memory usage grow sublinearly with respect to graph size.
A new hashing framework learns multiple hash codes for each image to improve hash bucket search efficiency.
problem Existing hashing methods fail to handle complex image retrieval scenarios efficiently.
method Multiple Code Hashing (MCH) framework with deep reinforcement learning.
result Significant improvement in hash bucket search performance compared to single-code methods.
A hashing technique reduces deep learning costs and energy usage.
problem Expensive matrix operations in deep learning training and testing.
method Randomized hashing for maximum inner product search and adaptive dropouts.
result Reduces overall computational cost by 95%, with 1% accuracy loss.
ADSH uses asymmetric deep hashing for faster training and better performance.
problem Efficiently utilizing supervised information for large-scale database in deep supervised hashing.
method ADSH learns a deep hash function only for query points and directly learns hash codes for database points.
result ADSH achieves state-of-the-art performance in real applications.
A new hashing method improves accuracy by learning an orthogonal transform.
problem Improving hashing accuracy for similarity search.
method Procrustean Orthogonal Sparse Hashing (POSH) method.
result POSH outperforms state-of-the-art hashing methods.
The paper compares different hashing schemes for their performance on structured data.
problem The performance of hashing schemes on structured input is not well understood.
method The paper compares mixed tabulation hashing, multiply-mod-prime hashing, and MurmurHash3.
result Mixed tabulation hashing performs similarly to truly random hashing but is faster and has a proven guarantee.
GANs visualize malware behavior for proactive protection.
problem Malware authors' advantage in testing and augmenting malicious code.
method GAN trained on distributed image representation of malware behaviors.
result Generated synthetic malware for adversarial training of anti-malware models.
Efficient Discrete Supervised Hashing improves cross-modal retrieval by preserving semantic correlations and reducing quantization error.
problem Challenges in preserving semantic correlations and reducing quantization error in cross-modal hashing for large-scale retrieval.
method Collective matrix factorization on heterogenous features and semantic embedding with class labels to learn hash codes efficiently.
result EDSH produces superior performance in both accuracy and scalability over existing methods.
FSDH is a fast supervised hashing method that outperforms existing methods.
problem Efficiently hashing large datasets for fast retrieval.
method FSDH uses a simple regression of class labels to hash codes, avoiding iterative discrete optimization.
result FSDH is significantly faster (12-151x) than existing methods like SDH and FastHash.
Develops a fast, accurate method for comparing networks.
problem Comparing networks with repeated observations and varying sizes/sparsity.
method A novel two-sample hypothesis testing method with theoretical guarantees.
result Outperforms existing tools in speed and accuracy, power-optimal.
New method improves nearest neighbor search using neural networks and graph partitioning.
problem Efficient nearest neighbor search in high-dimensional spaces.
method Developed a new framework for space partitioning using neural networks and graph partitioning.
result Neural LSH partitions outperform existing methods on standard benchmarks.
FlexCMH learns effective hashing codes from weakly-paired data.
problem Cross-modal hashing assumes perfect correspondence between samples, which is unrealistic.
method FlexCMH uses clustering-based matching to find potential correspondence and jointly optimizes it with hashing functions.
result FlexCMH achieves significantly better results than state-of-the-art methods.
New hashing method improves document retrieval precision.
problem Efficiently retrieving similar documents from large text databases.
method Pairwise supervised hashing with Bernoulli VAE and unbiased gradient estimator.
result Superior performance compared to existing methods.
We generated a dataset of 200 GB with 10^9 features, to test our recent b-bit minwise hashing algorithms for training very large-scale logistic regression and SVM. The results confirm our prior work that, compared with the VW hashing algorithm (which has the same variance as random projections), b-bit minwise hashing i…
Generative approach learns hash functions for efficient binary search.
problem Challenges in learning discrete hash functions for fast search.
method Generative approach using Minimum Description Length principle and stochastic distributional gradient.
result Significantly better retrieval results than existing methods.
Improves two-stage hashing methods for better image retrieval.
problem Developing efficient binary codes for image retrieval.
method Theoretical analysis and empirical improvements of two-stage hashing methods using high-capacity hash functions.
result Proposes a novel two-stage hashing method significantly outperforming previous studies.
Hash codes are a very efficient data representation needed to be able to cope with the ever growing amounts of data. We introduce a random forest semantic hashing scheme with information-theoretic code aggregation, showing for the first time how random forest, a technique that together with deep learning have shown spe…
BioHash improves similarity search performance using sparse high-dimensional hash codes.
problem Improving similarity search performance in high-dimensional data.
method BioHash produces sparse high-dimensional hash codes through a data-driven approach based on synaptic plasticity.
result BioHash outperforms previous hashing methods in various similarity search tasks.
New blockchain metrics improve cryptocurrency trading and prediction.
problem Improving trading and prediction in the volatile cryptocurrency market.
method Developed blockchain metrics based on public data from Bitcoin mining nodes.
result Blockchain metrics provide statistical advantage in trading Bitcoin assets.
Minwise hashing is the standard technique in the context of search and databases for efficiently estimating set (e.g., high-dimensional 0/1 vector) similarities. Recently, b-bit minwise hashing was proposed which significantly improves upon the original minwise hashing in practice by storing only the lowest b bits of e…
A new hashing method handles complex multi-level labels.
problem Handling complex multi-level labels in cross-modal data retrieval.
method Derives a semantic ranking list from feature and label information, integrates semantic ranking into deep cross-modal hashing.
result RDCMH outperforms other methods in cross-modal retrieval applications.
Enhances hashing for fast retrieval with correlated bits.
problem Fast retrieval and small memory footprint for large-scale information retrieval.
method Employing Boltzmann machine distribution as variational posterior to model correlations among hash code bits.
result Significant performance gains achieved by effectively modeling correlations among hash code bits.
This paper investigates semi-supervised hashing methods using variational autoencoders.
problem Semantic hashing with scarce labels.
method Two semi-supervised approaches: joint modeling and pairwise loss.
result The pairwise approach can improve hash quality with many labeled points but degrades with few labels.
Paper introduces EM-KSH and EM-SPLH methods for supervised hashing.
problem Efficiently optimize retrieval speed and storage cost while preserving semantic information.
method Convert supervised hashing formulations to CRF, solve consistency equations using linear approximation of sigmoid function.
result Experimental results show superior performance of EM-KSH and EM-SPLH.
A new framework THPI for hashing with auxiliary data.
problem Data sparsity in hashing for real-world applications.
method Transfer learning approach to extend ITQ method.
result Extensive experiments show the effectiveness of THPI.
Hashing converts continuous graph attributes to discrete labels for scalable graph kernel computation.
problem Handling graphs with continuous attributes using scalable kernels.
method Hash graph kernels derived from discrete kernels using randomized hash functions.
result Hash graph kernels are scalable and effective for graphs with continuous attributes.
Hyperplane hashing aims at rapidly searching nearest points to a hyperplane, and has shown practical impact in scaling up active learning with SVMs. Unfortunately, the existing randomized methods need long hash codes to achieve reasonable search accuracy and thus suffer from reduced search speed and large memory overhe…
New hashing methods improve entity resolution in conflict datasets.
problem Improving entity resolution in databases with unknown unique identifiers.
method Introducing and comparing new locality sensitive hashing methods.
result New hashing methods outperform existing approaches in conflict datasets.
mp-LSH shares hash codes for multiple dissimilarities.
problem Hash codes depend on dissimilarity, limiting query-time adjustments.
method mp-LSH shares hash codes for L2, cosine, inner product, and weighted sums.
result mp-LSH supports user-adjustable weights and feature importance.