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.
A method to uniformly sample graph-encoded surfaces of fixed size.
Efficient method for vertex embedding and community detection.
A fast graph embedding method for large graphs.
Improved graph embedding through refined linear transformation and community recovery.
The paper introduces a method for detecting principal communities and embedding vertices.
Paper explores embedding methods for detecting pseudo-cliques in random graphs, showing limitations and potential.
Graphs describe contact surgery on 3-manifolds.
Extends graph encoder embedding to weighted graphs and matrices.
A new graph encoder StarE models hyper-relational KGs, improving link prediction.
We solve the isomorphism problem for the whole class of Lins-Mandel gems (graphs encoded manifolds). We also present certain homeomorphisms of branched cyclic coverings of two-bridge hyperbolic links. As a consequence, we prove that, in in a wide subset of interesting cases, the isomorphism conditions for Lins-Mandel g…
In this paper, we consider recommender systems with side information in the form of graphs. Existing collaborative filtering algorithms mainly utilize only immediate neighborhood information and have a hard time taking advantage of deeper neighborhoods beyond 1-2 hops. The main caveat of exploiting deeper graph informa…
Graph neural networks benefit from a new initialization method that improves node learning.
Two CSSL-based methods improve graph classification with limited labeled data.
We introduce the Contextual Graph Markov Model, an approach combining ideas from generative models and neural networks for the processing of graph data. It founds on a constructive methodology to build a deep architecture comprising layers of probabilistic models that learn to encode the structured information in an in…
AGE improves graph embedding by smoothing features and iteratively enhancing node embeddings.
We describe a generalization of GKM theory for actions of arbitrary compact connected Lie groups. To an action satisfying the non-abelian GKM conditions we attach a graph encoding the structure of the non-abelian 1-skeleton, i.e., the subspace of points with isotopy rank at most one less than the rank of the acting gro…
This work formulates a novel song recommender system as a matrix completion problem that benefits from collaborative filtering through Non-negative Matrix Factorization (NMF) and content-based filtering via total variation (TV) on graphs. The graphs encode both playlist proximity information and song similarity, using …
Multilayer graphs encode different kind of interactions between the same set of entities. When one wants to cluster such a multilayer graph, the natural question arises how one should merge the information different layers. We introduce in this paper a one-parameter family of matrix power means for merging the Laplacia…
The study compares lamplighter graphs up to quasi-isometry using coarse topology.
The paper extends trisection theory to non-orientable 4-manifolds using colored triangulations.
Knowledge graphs have emerged as an important model for studying complex multi-relational data. This has given rise to the construction of numerous large scale but incomplete knowledge graphs encoding information extracted from various resources. An effective and scalable approach to jointly learn over multiple graphs …
We develop estimation for potentially high-dimensional additive structural equation models. A key component of our approach is to decouple order search among the variables from feature or edge selection in a directed acyclic graph encoding the causal structure. We show that the former can be done with nonregularized (r…
In earlier work we introduced the graph bracket polynomial of graphs with marked vertices, motivated by the fact that the Kauffman bracket of a link diagram D is determined by a looped, marked version of the interlacement graph associated to a directed Euler system of the universe graph of D. Here we extend the graph b…
We present a new paradigm for speeding up randomized computations of several frequently used functions in machine learning. In particular, our paradigm can be applied for improving computations of kernels based on random embeddings. Above that, the presented framework covers multivariate randomized functions. As a bypr…
Visualizing high-dimensional data has been a focus in data analysis communities for decades, which has led to the design of many algorithms, some of which are now considered references (such as t-SNE for example). In our era of overwhelming data volumes, the scalability of such methods have become more and more importa…
Ancestral graph models, introduced by Richardson and Spirtes (2002), generalize both Markov random fields and Bayesian networks to a class of graphs with a global Markov property that is closed under conditioning and marginalization. By design, ancestral graphs encode precisely the conditional independence structures t…
Visual rendering of graphs is a key task in the mapping of complex network data. Although most graph drawing algorithms emphasize aesthetic appeal, certain applications such as travel-time maps place more importance on visualization of structural network properties. The present paper advocates two graph embedding appro…
Signed graphs encode positive (attractive) and negative (repulsive) relations between nodes. We extend spectral clustering to signed graphs via the one-parameter family of Signed Power Mean Laplacians, defined as the matrix power mean of normalized standard and signless Laplacians of positive and negative edges. We pro…
New model generates larger molecules more effectively.
Graph-to-Tree Neural Networks improve structured input-output translation in tasks like semantic parsing and math word problems.
A novel disentangled graph autoencoder improves treatment effect estimation from networked observational data.
ABI adapts to graph data for fast, scalable inference.
Learning powerful data embeddings has become a center piece in machine learning, especially in natural language processing and computer vision domains. The crux of these embeddings is that they are pretrained on huge corpus of data in a unsupervised fashion, sometimes aided with transfer learning. However currently in …
CopulaGNN integrates graph representational and correlational roles for better node-level predictions.
Deep learning predicts drug side-effects from molecular graphs.
The regular genus of certain 4-manifolds is determined, providing new insights.
Missing data imputation (MDI) is a fundamental problem in many scientific disciplines. Popular methods for MDI use global statistics computed from the entire data set (e.g., the feature-wise medians), or build predictive models operating independently on every instance. In this paper we propose a more general framework…
MoReL models multi-omics data to find hidden molecular interactions.
Causal Component Analysis aims to recover latent variables with causal relationships.
CADGMM detects anomalies by capturing complex correlations in data.
A new method learns graph compression from data.
Transformer adapts to graphs with adaptive attention and auto-regressive decoding.
Online health communities such as the online breast cancer forum enable patients (i.e., users) to interact and help each other within various subforums, which are subsections of the main forum devoted to specific health topics. The changing nature of the users' activities in different subforums can be strong indicators…
For quantitative structure-property relationship (QSPR) studies in chemoinformatics, it is important to get interpretable relationship between chemical properties and chemical features. However, the predictive power and interpretability of QSPR models are usually two different objectives that are difficult to achieve s…
The idea of studying trisections of closed smooth -manifolds via (singular) triangulations, endowed with a suitable vertex-labelling by three colors, is due to Bell, Hass, Rubinstein and Tillmann, and has been applied by Spreer and Tillmann to colored triangulations associated to the so called simple crystallization…
Unified taxonomy for graph representation learning.
For node level graph encoding, a recent important state-of-art method is the graph convolutional networks (GCN), which nicely integrate local vertex features and graph topology in the spectral domain. However, current studies suffer from several drawbacks: (1) graph CNNs relies on Chebyshev polynomial approximation whi…
G1 uses RL to enhance LLMs' graph reasoning, improving performance on diverse tasks.