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.
Combines curvature descriptors with TDA for graph model evaluation.
New framework assesses graph-learning datasets for better evaluation.
New method uses contrastively trained GNNs for more reliable graph model evaluation.
This paper evaluates metrics for graph generative models, addressing common pitfalls.
New method evaluates financial graphs for stock trend forecasting.
Murakami-Ohtsuki-Yamada introduced an evaluation of certain oriented planar trivalent graphs with colored edges. This evaluation plays a key role in the evaluation of the colored HOMFLY polynomial of a link in 3-space and its Khovanov-Rozansky categorification. Our goal is is to give a generating series formula for the…
GraphBench creates a unified benchmark for graph learning tasks.
TUDataset provides benchmark datasets for graph learning.
PolyGraph Discrepancy improves graph generative model evaluation.
OGB provides diverse graph datasets for robust ML research.
This work benchmarks neural embeddings for link prediction in evolving knowledge graphs.
We investigate Relational Graph Attention Networks, a class of models that extends non-relational graph attention mechanisms to incorporate relational information, opening up these methods to a wider variety of problems. A thorough evaluation of these models is performed, and comparisons are made against established be…
A framework evaluates the impact of different modules in graph contrastive learning.
This paper evaluates LLMs on large graph property estimation tasks.
We introduce a fully coherent spin network amplitude whose expansion generates all SU(2) spin networks associated with a given graph. We then give an explicit evaluation of this amplitude for an arbitrary graph. We show how this coherent amplitude can be obtained from the specialization of a generating functional obtai…
Study error bounds in evaluating distributional computational graphs.
New distances for causal graphs improve evaluation of learned structures.
This work evaluates graph models' robustness to structural distributional shifts.
We focus our attention on the link prediction problem for knowledge graphs, which is treated herein as a binary classification task on neural embeddings of the entities. By comparing, combining and extending different methodologies for link prediction on graph-based data coming from different domains, we formalize a un…
With the rising interest in graph representation learning, a variety of approaches have been proposed to effectively capture a graph's properties. While these approaches have improved performance in graph machine learning tasks compared to traditional graph techniques, they are still perceived as techniques with limite…
GRETEL unifies GCE evaluation across various settings.
In this paper, we define the curvature dimension inequalities CD(m, K) on finite directed graphs modifying the case of undirected graphs. As a main result, we evaluate m and K on finite directed graphs.
We establish a relation between the trace evaluation in SO(3) topological quantum field theory and evaluations of a topological Tutte polynomial. As an application, a generalization of the Tutte golden identity is proved for graphs on the torus.
The study evaluates memory and capacity of graph embedding methods.
Study evaluates neural networks based on random graph structures and finds key performance indicators.
New relations for Penrose polynomial at n=4 and n=3.
Network structure optimization is a fundamental task in complex network analysis. However, almost all the research on Bayesian optimization is aimed at optimizing the objective functions with vectorial inputs. In this work, we first present a flexible framework, denoted graph Bayesian optimization, to handle arbitrary …
FinReflectKG builds a comprehensive financial knowledge graph from SEC filings, improving extraction quality.
The paper generalizes virtual knot theory using multiple types of virtual crossings.
We present RL-VAE, a graph-to-graph variational autoencoder that uses reinforcement learning to decode molecular graphs from latent embeddings. Methods have been described previously for graph-to-graph autoencoding, but these approaches require sophisticated decoders that increase the complexity of training and evaluat…
This paper evaluates knowledge graph completion models under the open-world assumption, revealing unexpected behavior of metrics.
Graph neural networks (GNNs) have emerged recently as a powerful architecture for learning node and graph representations. Standard GNNs have the same expressive power as the Weisfeiler-Leman test of graph isomorphism in terms of distinguishing non-isomorphic graphs. However, it was recently shown that this test cannot…
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…
Survey of graph adversarial learning tasks and their attacks and defenses.
This work improves policy-based training by proposing an evaluation balance objective for GFlowNets.
BetaExplainer improves GNN interpretability by masking unimportant edges.
Survey on deep models for graph generation.
In recent years, graph neural networks (GNNs) have emerged as a powerful neural architecture to learn vector representations of nodes and graphs in a supervised, end-to-end fashion. Up to now, GNNs have only been evaluated empirically -- showing promising results. The following work investigates GNNs from a theoretical…
CogDL simplifies graph deep learning experiments and benchmarks.
New method models aptamer libraries as Boltzmann-weighted graph ensembles for better affinity predictions.
The study evaluates GRL approaches and finds limitations in their applicability.
Causal inference relies on the structure of a graph, often a directed acyclic graph (DAG). Different graphs may result in different causal inference statements and different intervention distributions. To quantify such differences, we propose a (pre-) distance between DAGs, the structural intervention distance (SID). T…
Semi-supervised node classification in graphs is a fundamental problem in graph mining, and the recently proposed graph neural networks (GNNs) have achieved unparalleled results on this task. Due to their massive success, GNNs have attracted a lot of attention, and many novel architectures have been put forward. In thi…
Despite the recent successes in robotic locomotion control, the design of robot relies heavily on human engineering. Automatic robot design has been a long studied subject, but the recent progress has been slowed due to the large combinatorial search space and the difficulty in evaluating the found candidates. To addre…
Large-scale graph data in real-world applications is often not static but dynamic, i. e., new nodes and edges appear over time. Current graph convolution approaches are promising, especially, when all the graph's nodes and edges are available during training. When unseen nodes and edges are inserted after training, it …
Several structure learning algorithms have been proposed towards discovering causal or Bayesian Network (BN) graphs. The validity of these algorithms tends to be evaluated by assessing the relationship between the learnt and the ground truth graph. However, there is no agreed scoring metric to determine this relationsh…
PyKEEN 1.0 simplifies KGE model creation and optimization.
Generative models of graph structure have applications in biology and social sciences. The state of the art is GraphRNN, which decomposes the graph generation process into a series of sequential steps. While effective for modest sizes, it loses its permutation invariance for larger graphs. Instead, we present a permuta…