Knowledge graphs (KGs) typically contain temporal facts indicating relationships among entities at different times. Due to their incompleteness, several approaches have been proposed to infer new facts for a KG based on the existing ones-a problem known as KG completion. KG embedding approaches have proved effective fo…
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.
168,657 papers · 148 categories
Trend · papers per month
48 results for “static embeddings”
Introduces PELP for graph-enhanced word embeddings.
problem Combining graph side-information into static word embeddings.
method Probabilistic embeddings using Laplacian priors.
result Unified and flexible approach to various embedding methods.
Network representation learning in low dimensional vector space has attracted considerable attention in both academic and industrial domains. Most real-world networks are dynamic with addition/deletion of nodes and edges. The existing graph embedding methods are designed for static networks and they cannot capture evol…
A framework for stable dynamic network embeddings using static methods.
problem Dynamic network embedding in a nascent field.
method Using static network embedding methods on dilated unfolded adjacency matrices.
result Stable embeddings that preserve latent node behavior across time.
We generalize Brendle's geometric inequality considered in \cite{B} to static manifolds. The inequality bounds the integral of inverse mean curvature of an embedded mean-convex hypersurface by geometric data of the horizon. As a consequence, we obtain a reverse Penrose inequality on static asymptotically locally hyperb…
SFBoW provides sentence embeddings with predefined dimensions.
problem Sentence embeddings problem at document-level.
method Refinement of Fuzzy Bag-of-Words, predefined dimension.
result Competitive performances in Semantic Textual Similarity benchmarks.
Proves stability of spacetime Penrose inequality for spherical symmetric initial data.
problem Stability of the Penrose inequality for spherical symmetric spacetimes.
method Formulated and proved stability statement using spherical symmetry and asymptotically flat initial data.
result Initial data must arise from an isometric embedding into a static spacetime close to Schwarzschild spacetime.
Predict stock movement with news headlines using BERT embeddings.
problem Predicting stock price movement after financial news.
method Fine-Tuned Contextualized-Embedding Recurrent Neural Network (FT-CE-RNN) using BERT.
result Obtains state-of-the-art results on stock movement prediction task.
Global and uniqueness properties of stationary and static spacetimes with outer trapped surfacesgr-qc
Global properties of maximal future Cauchy developments of stationary, m-dimensional asymptotically flat initial data with an outer trapped boundary are analyzed. We prove that, whenever the matter model is well posed and satisfies the null energy condition, the future Cauchy development of the data is a black hole spa…
Study null energy condition impacts on special hypersurfaces in static spacetimes.
problem Effects of null energy condition on totally umbilic hypersurfaces.
method Characterization of embedded surfaces and photon surfaces using Alexandrov Theorem and other methods.
result Full characterization of embedded surfaces with constant spacetime mean curvature.
EPNE models evolving network patterns for better predictions.
problem Capturing evolving patterns in dynamic networks.
method EPNE models temporal network evolution using causal convolutions and a temporal objective function.
result EPNE outperforms other methods in various prediction tasks.
Ancient curve flows classified into specific types.
problem Classifying ancient finite-entropy curve shortening flows.
method Proving flow types through mathematical analysis.
result Ancient flows are one of several specific types.
Self-Supervised Learning of Contextual Embeddings for Link Prediction in Heterogeneous Networkscs.LG
SLiCE learns contextual node embeddings for link prediction in heterogeneous networks.
problem Link prediction requires specific contextual information not captured by static node embeddings.
method Self-supervised pre-training with localized attention mechanisms.
result SLiCE significantly outperforms existing methods on link prediction tasks.
Networks evolve continuously over time with the addition, deletion, and changing of links and nodes. Such temporal networks (or edge streams) consist of a sequence of timestamped edges and are seemingly ubiquitous. Despite the importance of accurately modeling the temporal information, most embedding methods ignore it …
Predictive Sparse Manifold Transform learns dynamic video sequences.
problem Learning and predicting natural dynamics in video sequences.
method Two-layer framework: sparse coding and manifold learning.
result PSMT with dynamic embedding space outperforms static baselines in future frame prediction.
CTGCN learns dynamic graph embeddings preserving both local and global graph structure.
problem Learning node representations for evolving graphs while preserving both local and global graph structure.
method CTGCN uses k-core based temporal graph convolutional network to learn dynamic graph embeddings.
result CTGCN outperforms existing methods in link prediction and structural role classification.
This study improves sentence embeddings from BERT models.
problem Capturing the underlying meaning of sentences using BERT models.
method Comprehensive review and testing of various sentence embedding extraction and refinement methods.
result Representation-shaping techniques significantly improve sentence embeddings from BERT-based and simple baseline models.
Proposes RNNE for dynamic network embedding.
problem Handling dynamic networks with changing node and edge counts.
method Recurrent Neural Network Embedding (RNNE) for topologically evolving graphs and temporal graphs.
result RNNE outperforms state-of-the-art algorithms in network reconstruction, classification, and link prediction.
Framework for dynamic node embeddings from graph streams.
problem Temporal prediction-based applications using graph stream data.
method ε-graph time-series representation, temporal reachability graphs, weighted temporal summary graphs.
result Dynamic embedding methods achieve better predictive performance.
Study of quasilocal mass using isometric embedding in various spacetimes.
problem Understanding quasilocal mass in different spacetimes.
method Application of isometric embedding theory to quasilocal mass.
result Recent progress in quasilocal mass calculations with specific spacetimes.
Loss-guided training accelerates node embedding methods on graphs.
problem Training efficiency in graph learning methods with implicit positive examples.
method Dynamic adjustment of training distribution based on loss values.
result Significant acceleration in training and computation over static methods.
MTHetGNN models complex relations in multivariate time series forecasting.
problem Complex relations among variables in multivariate time series forecasting.
method Designs a relation embedding module and a temporal embedding module, using graph neural networks and CNNs.
result Achieves state-of-the-art results in multivariate time series forecasting.
DGRCL integrates dynamic and static graph relations for financial market prediction.
problem Capturing the evolving nature of stock markets while considering both temporal changes and static relational structures.
method Dynamic Graph Representation with Contrastive Learning (DGRCL) framework, including Embedding Enhancement (EE) and Contrastive Constrained Training (CCT) modules.
result DGRCL significantly outperforms state-of-the-art TGL baselines on NASDAQ and NYSE datasets.
Positive mass theorem for tori with scalar curvature bounds.
problem Proving positivity of static quasi-local mass for tori.
method Generalization of Shi-Tam result to 2-tori with specific curvature and scalar curvature bounds.
result Total weighted mean curvature of 2-tori is not greater than that of an isometric embedding into the Kottler manifold.
Recently, graph neural networks (GNNs) have proved to be suitable in tasks on unstructured data. Particularly in tasks as community detection, node classification, and link prediction. However, most GNN models still operate with static relationships. We propose the Graph Learning Network (GLN), a simple yet effective p…
Representation learning on graphs has emerged as a powerful mechanism to automate feature vector generation for downstream machine learning tasks. The advances in representation on graphs have centered on both homogeneous and heterogeneous graphs, where the latter presenting the challenges associated with multi-typed n…
Dynamic Word Embeddingsstat.ML
We present a probabilistic language model for time-stamped text data which tracks the semantic evolution of individual words over time. The model represents words and contexts by latent trajectories in an embedding space. At each moment in time, the embedding vectors are inferred from a probabilistic version of word2ve…
DVE models dynamic changes in feature embeddings for better sequence-aware applications.
problem Dynamic characterization of feature variations in time-varying data.
method Dynamic Variational Embedding (DVE) using recurrent neural networks.
result DVE models intrinsic nature and temporal variation of nodes effectively.
Given a Riemannian 3-ball of non-negative scalar curvature, Bartnik conjectured that admits an asymptotically flat (AF) extension (without horizons) of the least possible ADM mass, and that such a mass-minimizer is an AF solution to the static vacuum Einstein equations, uniquely determined b…
In this work, we present a method for node embedding in temporal graphs. We propose an algorithm that learns the evolution of a temporal graph's nodes and edges over time and incorporates this dynamics in a temporal node embedding framework for different graph prediction tasks. We present a joint loss function that cre…
We show that removing sigmoid transformation in the skip-gram with negative sampling (SGNS) objective does not harm the quality of word vectors significantly and at the same time is related to factorizing a squashed shifted PMI matrix which, in turn, can be treated as a connection probabilities matrix of a random graph…
We obtain bounds on the distribution of the maximum of a martingale with fixed marginals at finitely many intermediate times. The bounds are sharp and attained by a solution to -marginal Skorokhod embedding problem in Obłój and Spoida [An iterated Azéma-Yor type embedding for finitely many marginals (2013) Preprint]…
DynamicGEM is an open-source Python library for learning node representations of dynamic graphs. It consists of state-of-the-art algorithms for defining embeddings of nodes whose connections evolve over time. The library also contains the evaluation framework for four downstream tasks on the network: graph reconstructi…
Study classifies static potentials on 3-manifolds, proving one-dimensionality under specific conditions.
problem Classifying the dimension of static potentials on 3-manifolds.
method Analysis of relative zero sets of static potentials, using Miao and Tam's technique.
result Proves one-dimensionality of static potentials under specific conditions.
With the celebrated success of deep learning, some attempts to develop effective methods for detecting malicious PowerShell programs employ neural nets in a traditional natural language processing setup while others employ convolutional neural nets to detect obfuscated malicious commands at a character level. While the…
New static vacuum metrics confirmed for near Euclidean boundary data.
problem Establishing sufficient conditions for near Euclidean boundary data in static vacuum metrics.
method Using new arguments from studying the conjecture for arbitrary static vacuum metrics.
result Any hypersurface in a dense subfamily is static regular.
Adaptive portfolio outperforms static alternatives by 120% over 5 years.
problem Achieving strong and stable long-term performance in diversified portfolios.
method RL-BHRP: A two-level, learning-based approach that adjusts sector and stock exposures dynamically.
result Adaptive portfolio outperforms static alternatives by 120% over 5 years.
Most of real-world graphs are dynamic, i.e., they change over time by a sequence of update operations. While the regression problem has been studied for static graphs and temporal graphs, it is not investigated for general dynamic graphs. In this paper, we study regression over dynamic graphs. First, we present the not…
Curve shortening flow is not unique on certain metrics.
problem Non-uniqueness of curve shortening flow on specific metrics.
method Formulated a uniqueness conjecture and constructed a non-static solution.
result Curve shortening flow is not unique on a non-flat metric on the plane.
Static vacuum extensions with prescribed Bartnik boundary data near a general static vacuum metricmath.DG
Extends static vacuum metrics with specific boundary conditions.
problem Proving the existence of static vacuum metrics with prescribed boundary data.
method Introducing static regular types (I) and (II), showing local well-posedness, and confirming Bartnik's conjecture.
result Confirms Bartnik's static vacuum extension conjecture for a broad range of boundary conditions.
Improves scalability and robustness of dynamic graph clustering.
problem Scalability and robustness issues in matrix factorization methods for dynamic graphs.
method Temporal separated matrix factorization, bi-clustering regularization, selective embedding updating.
result Demonstrated scalability, robustness, and effectiveness on synthetic and real-world benchmarks.
We classify static manifolds which admit more than one static decomposition whenever a condition on the curvature is fullfilled. For this, we take a standard static vector field and analyze its associated one parameter family of projections onto the base. We show that the base itself is a static manifold and the warpin…
Study of 3D vacuum static spaces with specific curvature properties.
problem Classifying 3D vacuum static spaces with certain curvature conditions.
method Used generalized maximum principle to classify 3D spaces.
result Gave a complete classification of 3D complete vacuum static spaces.
DyHATR learns dynamic heterogeneous networks for better link prediction.
problem Learning effective representations of dynamic heterogeneous networks for link prediction.
method Hierarchical attention for heterogeneous information and temporal RNN for evolutionary patterns.
result DyHATR significantly outperforms state-of-the-art baselines on link prediction tasks.
New rigidity theorem on static manifolds with boundary.
problem Static metrics on manifolds with boundary.
method Obata-type rigidity theorem, sufficient geometric conditions.
result Scalar curvature map can be locally surjective at static metrics on manifolds with boundary.
Geometric inequalities for static convex domains in hyperbolic space proved.
problem Proving geometric inequalities for static convex domains in hyperbolic space.
method Using static convexity of flow hypersurfaces, new inequalities are derived.
result New family of geometric inequalities for static convex domains in hyperbolic space.
With online payment platforms being ubiquitous and important, fraud transaction detection has become the key for such platforms, to ensure user account safety and platform security. In this work, we present a novel method for detecting fraud transactions by leveraging patterns from both users' static profiles and users…
The paper classifies vacuum static spaces with harmonic curvature.
problem Classifying vacuum static spaces with harmonic curvature.
method Extending the 4-dimensional work by Kim-Shin, the paper classifies -dimensional spaces ().
result New counterexamples to the Fischer-Marsden conjecture on compact vacuum static spaces.