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.
MXGNet tackles visual reasoning tasks using graph neural networks.
G1 uses RL to enhance LLMs' graph reasoning, improving performance on diverse tasks.
Inferring new facts from existing knowledge graphs (KG) with explainable reasoning processes is a significant problem and has received much attention recently. However, few studies have focused on relation types unseen in the original KG, given only one or a few instances for training. To bridge this gap, we propose Co…
Improved RL for knowledge graph reasoning with entity types.
Survey of neurosymbolic AI methods for reasoning over knowledge graphs.
GraphToken encodes structured data for LLMs, improving graph reasoning tasks.
Graph Neural Networks align with dynamic programming, improving algorithmic reasoning.
Most research in reading comprehension has focused on answering questions based on individual documents or even single paragraphs. We introduce a neural model which integrates and reasons relying on information spread within documents and across multiple documents. We frame it as an inference problem on a graph. Mentio…
The AI2 Reasoning Challenge (ARC), a new benchmark dataset for question answering (QA) has been recently released. ARC only contains natural science questions authored for human exams, which are hard to answer and require advanced logic reasoning. On the ARC Challenge Set, existing state-of-the-art QA systems fail to s…
Method integrates logical rules into neural multi-hop reasoning for drug repurposing.
Sparse hypergraph neural networks improve reasoning in large knowledge graphs.
Knowledge graph reasoning, which aims at predicting the missing facts through reasoning with the observed facts, is critical to many applications. Such a problem has been widely explored by traditional logic rule-based approaches and recent knowledge graph embedding methods. A principled logic rule-based approach is th…
A general graph-structured neural network architecture operates on graphs through two core components: (1) complex enough message functions; (2) a fixed information aggregation process. In this paper, we present the Policy Message Passing algorithm, which takes a probabilistic perspective and reformulates the whole inf…
CFRecs uses counterfactual reasoning to improve graph-based recommendations in real estate.
This paper evaluates LLMs on large graph property estimation tasks.
It is feasible and practically-valuable to bridge the characteristics between graph neural networks (GNNs) and logical reasoning. Despite considerable efforts and successes witnessed to solve Boolean satisfiability (SAT), it remains a mystery of GNN-based solvers for more complex predicate logic formulae. In this work,…
Neural-symbolic model improves link prediction in knowledge graphs.
Graph signal processing detects hallucinations in large language models.
FinReflectKG benchmarks financial QA by linking relevant context from a financial KG, improving model performance and efficiency.
AI uses KGs to assess economic impact of selective lockdowns on Italian companies.
Method guarantees coherent factuality for language model outputs in reasoning tasks.
Lots of learning tasks require dealing with graph data which contains rich relation information among elements. Modeling physics systems, learning molecular fingerprints, predicting protein interface, and classifying diseases demand a model to learn from graph inputs. In other domains such as learning from non-structur…
A new framework for knowledge graph embedding using sheaves.
We study the statistical behavior of reasoning probes in a stylized model of iterative computation inspired by neural algorithmic reasoning. The underlying computation is given by a looped Boolean circuit whose graph is a perfect -ary tree (), with outputs recursively fed back as inputs across computation ro…
This paper addresses the challenging problem of retrieval and matching of graph structured objects, and makes two key contributions. First, we demonstrate how Graph Neural Networks (GNN), which have emerged as an effective model for various supervised prediction problems defined on structured data, can be trained to pr…
Graph-based approach repairs programs from diagnostic feedback.
Introduces data augmentation for graph convolutional networks, proposing Monte Carlo Graph Learning.
Semantic Web knowledge representation standards, and in particular RDF and OWL, often come endowed with a formal semantics which is considered to be of fundamental importance for the field. Reasoning, i.e., the drawing of logical inferences from knowledge expressed in such standards, is traditionally based on logical d…
Shapley Flow interprets model predictions using a graph-based approach to feature importance.
XLVINs improve deep reinforcement learning by combining self-supervised learning and neural algorithmic reasoning.
In this paper we give a method to construct Heegaard splittings of oriented graph manifolds with orientable bases. A graph manifold is a closed -manifold admitting only Seifert-fibered pieces in its Jaco-Shalen decomposition; for technical reasons, we restrict our attention to the fully oriented case, i.e. both the …
Fact verification (FV) is a challenging task which requires to retrieve relevant evidence from plain text and use the evidence to verify given claims. Many claims require to simultaneously integrate and reason over several pieces of evidence for verification. However, previous work employs simple models to extract info…
We investigate graph neural networks for multi-relational data.
The dominant paradigm for relation prediction in knowledge graphs involves learning and operating on latent representations (i.e., embeddings) of entities and relations. However, these embedding-based methods do not explicitly capture the compositional logical rules underlying the knowledge graph, and they are limited …
Study on HyperGNNs' expressiveness and structural generalization.
Effectively combining logic reasoning and probabilistic inference has been a long-standing goal of machine learning: the former has the ability to generalize with small training data, while the latter provides a principled framework for dealing with noisy data. However, existing methods for combining the best of both w…
A framework isolates VQA reasoning from perception for better model evaluation.
A novel method for visual question answering using scene graphs and reinforcement learning.
CaT-GNN improves credit card fraud detection by integrating causal reasoning into GNNs.
CSML learns causal structures for few-shot learning.
Introduces Spectral Graph Network combining spatial and spectral message passing.
Causal reasoning has been an indispensable capability for humans and other intelligent animals to interact with the physical world. In this work, we propose to endow an artificial agent with the capability of causal reasoning for completing goal-directed tasks. We develop learning-based approaches to inducing causal kn…
Proposes CLRS benchmark to evaluate algorithmic reasoning.
We propose a novel method for fact-checking on knowledge graphs based on debate dynamics. The underlying idea is to frame the task of triple classification as a debate game between two reinforcement learning agents which extract arguments -- paths in the knowledge graph -- with the goal to justify the fact being true (…
Graph Neural Network (GNN) research has concentrated on improving convolutional layers, with little attention paid to developing graph pooling layers. Yet pooling layers can enable GNNs to reason over abstracted groups of nodes instead of single nodes. To close this gap, we propose a graph pooling layer relying on the …
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…
FinCARE combines financial data and AI reasoning to improve causal analysis of financial performance.
Neural networks have succeeded in many reasoning tasks. Empirically, these tasks require specialized network structures, e.g., Graph Neural Networks (GNNs) perform well on many such tasks, but less structured networks fail. Theoretically, there is limited understanding of why and when a network structure generalizes be…