The study evaluates memory and capacity of graph embedding methods.
problem Assessing the memory and capacity of graph embedding methods.
method Not specified in the abstract provided.
result Not specified in the abstract provided.
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.
168,695 papers · 148 categories
Trend · papers per month
48 results for “memory embeddings”
The paper explores how gradient descent trains associative memories, revealing oscillations and convergence issues.
problem Training dynamics of associative memories in overparameterized and underparameterized settings.
method Reduction to particle system dynamics, theory, and experiments.
result Oscillatory transitory regimes and benign loss spikes in overparameterized settings, suboptimal memorization in underparameterized settings.
Embedding representations power machine intelligence in many applications, including recommendation systems, but they are space intensive -- potentially occupying hundreds of gigabytes in large-scale settings. To help manage this outsized memory consumption, we explore mixed dimension embeddings, an embedding layer arc…
The paper explores how word embeddings affect the stability of downstream NLP models.
problem Small changes in training data can cause significant changes in model predictions.
method Empirical and theoretical analysis of embedding instability, including the introduction of eigenspace instability measure.
result Increasing embedding memory can reduce the disagreement in predictions by 5% to 37%.
Compositional Embeddings Using Complementary Partitions for Memory-Efficient Recommendation Systemscs.LG
Modern deep learning-based recommendation systems exploit hundreds to thousands of different categorical features, each with millions of different categories ranging from clicks to posts. To respect the natural diversity within the categorical data, embeddings map each category to a unique dense representation within a…
Typical large-scale recommender systems use deep learning models that are stored on a large amount of DRAM. These models often rely on embeddings, which consume most of the required memory. We present Bandana, a storage system that reduces the DRAM footprint of embeddings, by using Non-volatile Memory (NVM) as the prim…
Deep models store facts in geometric embeddings, not just associative memory.
problem Understanding how deep models store and utilize atomic facts.
method Identified geometric memory, contrasting with associative lookup.
result Geometric memory transforms hard reasoning into easy tasks.
TASO optimizes CNN models for memory-constrained devices.
problem Large CNN models are too resource-intensive for mobile devices.
method Integer Linear Programming (ILP) for selecting operations and workspace allocation.
result 8x speedup and 2.2x reduction in memory usage compared to greedy algorithms.
METEOR learns efficient representations from multi-modal data streams.
problem Efficiently interpreting multi-modal information in complex environments.
method METEOR learns compact representations by sharing parameters within semantically meaningful groups and preserving domain-agnostic semantics.
result METEOR reduces memory usage by around 80% compared to conventional methods.
The computation of convolution layers in deep neural networks typically rely on high performance routines that trade space for time by using additional memory (either for packing purposes or required as part of the algorithm) to improve performance. The problems with such an approach are two-fold. First, these routines…
SAGE improves memory efficiency by selectively adding, merging, or ignoring new facts.
problem Efficiently managing new facts in agentic LLMs to avoid costly write-time reasoning.
method SAGE uses a von Mises-Fisher-based density estimator to score and route candidate facts.
result SAGE achieves the best average token-F1 on LoCoMo and reduces add-phase API cost by 3.4x on GPT-4o-mini.
This paper proposes a hardware-oriented dropout algorithm, which is efficient for field programmable gate array (FPGA) implementation. In deep neural networks (DNNs), overfitting occurs when networks are overtrained and adapt too well to training data. Consequently, they fail in predicting unseen data used as test data…
POET enables large neural network training on tiny devices with reduced energy.
problem Training large neural networks on memory-limited edge devices.
method Jointly optimizes rematerialization and paging for memory reduction, formulating an MILP for energy-efficient training.
result POET trains ResNet-18 and BERT within Cortex-M memory constraints, outperforming current methods in energy efficiency.
A method models nonlinear dynamics from data using barycentric coordinates and memory.
problem Modeling complex dynamical systems from data.
method SPA for data projection, barycentric coordinates, delay-embedding theorem for memory.
result Stable models of chaotic dynamics and attractors are reproduced.
The paper studies scaling laws for associative memory mechanisms.
problem Understanding and optimizing learning and memorization processes.
method High-dimensional matrices of outer products of embeddings, relating to transformer models. Derived scaling laws with sample and parameter sizes. Extensive numerical experiments.
result Precise scaling laws and statistical efficiency of estimators.
The paper tackles scalability issues in Graph Representation Learning.
problem Prohibitive time and memory complexities in Graph Representation Learning.
method Leveraging the K-Core Decomposition property of Graphs to reduce time and memory consumption.
result Proposed techniques significantly reduce computational resources without compromising embedding quality.
InstantEmbedding efficiently generates node representations with less computation and memory.
problem Efficiently generating local node representations for large graphs.
method Local PageRank computations in sublinear time.
result Significantly faster and less memory-intensive than traditional methods.
In the advent of big data era, interactive visualization of large data sets consisting of M*10^5+ high-dimensional feature vectors of length N (N ~ 10^3+), is an indispensable tool for data exploratory analysis. The state-of-the-art data embedding (DE) methods of N-D data into 2-D (3-D) visually perceptible space (e.g.…
Embed-KCPD segments text without labels, outperforming baselines.
problem Unsupervised text segmentation is challenging due to lack of boundary labels.
method Embed-KCPD represents sentences as embeddings and estimates boundaries via penalized KCPD.
result Embed-KCPD outperforms strong unsupervised baselines across benchmarks.
A new method uses matrix sketches for efficient graph clustering in dynamic environments.
problem Efficiently clustering large, dynamic graphs in distributed memory systems.
method Inspired by spectral clustering, the approach uses random dimension-reducing projections to derive matrix sketches.
result The method produces embeddings that yield performant clustering results in a fully-dynamic stochastic block model stream.
Improved recommendation systems using multi-layer embeddings reduce model size while maintaining accuracy.
problem Improving model accuracy in recommendation systems while minimizing model size.
method Introducing a multi-layer embedding training (MLET) architecture that trains embeddings via a sequence of linear layers.
result Substantial advantages in model accuracy and memory footprint are achieved with reduced embedding dimensions.
Evaluating KGR10 Polish word embeddings in the recognition of temporal expressions using BiLSTM-CRFcs.CL
The article introduces a new set of Polish word embeddings, built using KGR10 corpus, which contains more than 4 billion words. These embeddings are evaluated in the problem of recognition of temporal expressions (timexes) for the Polish language. We described the process of KGR10 corpus creation and a new approach to …
PCA reduces language model embeddings to improve speed and memory efficiency.
problem High-dimensional embeddings in RAG models cause scalability issues.
method Used Principal Component Analysis (PCA) to compress embeddings.
result Reducing from 3,072 to 110 dimensions provides significant speedup and memory reduction.
Recent studies on automatic neural architectures search have demonstrated significant performance, competitive to or even better than hand-crafted neural architectures. However, most of the existing network architecture tend to use residual, parallel structures and concatenation block between shallow and deep features …
PoET-BiN reduces power consumption in neural networks on embedded devices.
problem Power inefficiency in neural network implementations on embedded platforms.
method Look-Up Table based implementation with a modified Decision Tree approach.
result Near state-of-the-art results with up to 6 orders of magnitude energy reduction.
Probabilistic hash embeddings improve online learning of categorical features.
problem Online learning of categorical features with changing vocabulary.
method Probabilistic hash embedding (PHE) with Bayesian online learning.
result PHE mitigates forgetting and maintains high performance in online settings.
SGQuant reduces GNN memory usage without significant accuracy loss.
problem High memory consumption in GNNs limits their applicability on memory-constrained devices.
method Proposes a specialized GNN quantization scheme (SGQuant) with a quantization algorithm, fine-tuning scheme, and multi-granularity strategy.
result SGQuant reduces GNN memory footprint from 4.25x to 31.9x with minimal accuracy loss.
New model captures long-term memory effects in epidemic dynamics.
problem Identifying memory effects in disease progression and recovery.
method Physics-informed neural networks (PINN) with fractional SEIRD model.
result Fractional memory order improves predictive performance over classical models.
Continuous representation of words is a standard component in deep learning-based NLP models. However, representing a large vocabulary requires significant memory, which can cause problems, particularly on resource-constrained platforms. Therefore, in this paper we propose an isotropic iterative quantization (IIQ) appr…
Production recommendation systems rely on embedding methods to represent various features. An impeding challenge in practice is that the large embedding matrix incurs substantial memory footprint in serving as the number of features grows over time. We propose a similarity-aware embedding matrix compression method call…
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.
In this paper, we introduce a novel layer designed to be used as the output of pre-trained neural networks in the context of classification. Based on Associative Memories, this layer can help design Deep Neural Networks which support incremental learning and that can be (partially) trained in real time on embedded devi…
Muon spectral optimizer outperforms SGD in associative memory tasks.
problem Understanding the advantage of spectral optimizers in learning associative memory.
method Linear associative memory problem, Gaussian inputs and outputs, power law frequency distribution, thresholded gradient approximation.
result Muon significantly outperforms SGD in storage capacity and recovery rates.
Embedding layers are commonly used to map discrete symbols into continuous embedding vectors that reflect their semantic meanings. Despite their effectiveness, the number of parameters in an embedding layer increases linearly with the number of symbols and poses a critical challenge on memory and storage constraints. I…
Paper proposes a novel graph recovery attack from node embeddings.
problem Privacy risks of integrating graph embeddings with machine learning pipelines.
method Model-agnostic graph recovery attack exploiting preserved structural information in node embeddings.
result Adversaries can recover graph edges with decent accuracy from node embeddings alone.
We analyse perception and memory, using mathematical models for knowledge graphs and tensors, to gain insights into the corresponding functionalities of the human mind. Our discussion is based on the concept of propositional sentences consisting of \textit{subject-predicate-object} (SPO) triples for expressing elementa…
Learning embeddings of entities and relations is an efficient and versatile method to perform machine learning on relational data such as knowledge graphs. In this work, we propose holographic embeddings (HolE) to learn compositional vector space representations of entire knowledge graphs. The proposed method is relate…
We propose a new algorithm for training neural networks with binary activations and multi-level weights, which enables efficient processing-in-memory circuits with embedded nonvolatile memories (eNVM). Binary activations obviate costly DACs and ADCs. Multi-level weights leverage multi-level eNVM cells. Compared to exis…
TristouNet is a neural network architecture based on Long Short-Term Memory recurrent networks, meant to project speech sequences into a fixed-dimensional euclidean space. Thanks to the triplet loss paradigm used for training, the resulting sequence embeddings can be compared directly with the euclidean distance, for s…
Automated framework optimizes DNN deployment on Arm CPUs.
problem Lack of globally optimised DNN deployment across software levels.
method Reinforcement Learning search for automated design space exploration.
result Up to 4x improvement in performance and 2x reduction in memory.
Recent empirical results on long-term dependency tasks have shown that neural networks augmented with an external memory can learn the long-term dependency tasks more easily and achieve better generalization than vanilla recurrent neural networks (RNN). We suggest that memory augmented neural networks can reduce the ef…
PyKEEN 1.0 simplifies KGE model creation and optimization.
problem Training and evaluating knowledge graph embeddings (KGEs).
method Composes KGEMs with various interaction models, training approaches, and loss functions. Implements automatic memory optimization and extensive HPO functionalities.
result PyKEEN 1.0 streamlines KGE model creation and optimization.
The ability to look multiple times through a series of pose-adjusted glimpses is fundamental to human vision. This critical faculty allows us to understand highly complex visual scenes. Short term memory plays an integral role in aggregating the information obtained from these glimpses and informing our interpretation …
Deep Fried Convnetscs.LG
The fully connected layers of a deep convolutional neural network typically contain over 90% of the network parameters, and consume the majority of the memory required to store the network parameters. Reducing the number of parameters while preserving essentially the same predictive performance is critically important …
Improved deep learning model deployment on tiny MCUs with mixed-precision quantization.
problem Memory limitations prevent accurate deployment of DNN models on tiny MCUs.
method Automated mixed-precision quantization using Reinforcement Learning for MCU constraints.
result Mixed-precision models achieve high accuracy with uniform quantization policies.
Continuous representations have been widely adopted in recommender systems where a large number of entities are represented using embedding vectors. As the cardinality of the entities increases, the embedding components can easily contain millions of parameters and become the bottleneck in both storage and inference du…
Efficient ANN search for sparse embeddings in ads targeting.
problem Efficiently searching near neighbors in sparse data for applications like ads targeting.
method Graph-based ANN algorithms (HNSW, chi-square two-tower model, Sign Cauchy Projections).
result Sparse embeddings and ANN algorithms improve efficiency in EBR applications.
Deep learning natural language processing models often use vector word embeddings, such as word2vec or GloVe, to represent words. A discrete sequence of words can be much more easily integrated with downstream neural layers if it is represented as a sequence of continuous vectors. Also, semantic relationships between w…