Research
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.

168,742 papers · 148 categories

Trend · papers per month

95190285380 · Jun 202019922001200920172026
48 results for symbolic graph embedding

SGE learns symbolic node representations from relational data.

problem Mining insights from complex, real-world systems.
method SGE uses frequent pattern mining on a node's neighborhood to learn symbolic node representations.
result SGE outperforms shallow node embedding methods on a venue classification task.

Neural-symbolic model improves link prediction in knowledge graphs.

problem Effective relational learning and reasoning for AI systems.
method Neural-symbolic graph neural network that learns over all paths in knowledge graphs.
result Neural-symbolic model outperforms path-based approaches in link prediction.

Representation learning has become an invaluable approach for learning from symbolic data such as text and graphs. However, while complex symbolic datasets often exhibit a latent hierarchical structure, state-of-the-art methods typically learn embeddings in Euclidean vector spaces, which do not account for this propert…

2017-05-22abs ↗pdf ↗

Explores tensor products in hyperdimensional computing.

problem Understanding tensor products in hyperdimensional computing.
method Generalized results from graph embeddings to vector symbolic architectures and hyperdimensional computing.
result Tensor product is the most general and expressive representation with errorless unbinding and detection.

New algorithm improves interpretability in sequence classification.

problem Lack of human-independent interpretability metrics in sequence classification.
method Combines linear classifiers with background knowledge embeddings to create a new feature space.
result Preserves predictive power while delivering more interpretable models.

Neural networks learn symbolic structure to perform compositional tasks.

problem How neural networks perform well on compositional tasks without explicit representations.
method ROLE analysis to uncover symbolic structure in recurrent neural networks.
result Neural networks converge to solutions that implicitly represent symbolic structure.

EPSTE: A geometric token and deep learning approach to estimating transfer entropy in neuroimaging time series

problem Inferring directed interactions between neural systems from EEG and MEG
method Reframing TE estimation as a learnable problem operating on structured symbolic representations
result EPSTE achieves near-perfect recovery of ground-truth directed structure and significantly lower absolute error than the baseline

Study shows how transformers classify symbols without naming them, proving a margin-versus-collision criterion.

problem How transformers classify symbols without naming them.
method Logistic classification analysis of transformer-kernel regime, colored collision graph.
result Decomposes learned predictor into ideal template-level classifier and finite-sample perturbation.

We introduce an approach for imposing physically motivated inductive biases on graph networks to learn interpretable representations and improved zero-shot generalization. Our experiments show that our graph network models, which implement this inductive bias, can learn message representations equivalent to the true fo…

2019-09-12abs ↗pdf ↗

Extract symbolic models from deep learning with inductive biases.

problem Interpreting and discovering physical principles from deep neural networks.
method Introduce strong inductive biases in GNNs, encourage sparse latent representations, apply symbolic regression.
result Extracted symbolic equations from neural networks, including known force laws and new analytic formulas.

We generalize the colored Alexander invariant of knots to an invariant of graphs, and we construct a face model for this invariant by using the corresponding 6j-symbol, which comes from the non-integral representations of the quantum group U_q(sl_2). We call it the SL(2, C) quantum 6j-symbol, and show its relation to t…

2010-05-24abs ↗pdf ↗

Paper proposes an algorithm to reconstruct optimal model structure from graph adjacency matrix.

problem Optimal model structure reconstruction from weighted colored graph adjacency matrix.
method Uses prize-collecting Steiner tree algorithm to reconstruct minimum spanning tree.
result Demonstrates the effectiveness of the prize-collecting Steiner tree algorithm for model structure reconstruction.

Diffusion models generate music sequences without autoregressive loops.

problem Generating music sequences from symbolic data using diffusion models.
method Parameterize discrete symbolic data in continuous latent space, train diffusion model, generate sequences through reverse process.
result Strong unconditional generation and post-hoc conditional infilling compared to autoregressive models.

Hybrid model learns novel handwritten characters better than neural or symbolic models alone.

problem Generating novel yet structured concepts.
method Neuro-symbolic model combining neural networks and probabilistic programs.
result Hybrid model outperforms alternative models in learning and generalizing novel handwritten characters.

The paper connects quantum 6j6j-symbols to tetrahedra volumes via discrete Fourier transforms.

problem Understanding the asymptotic behavior of quantum 6j6j-symbols and their relation to 3-manifold invariants.
method Proposing and proving a conjecture linking discrete Fourier transforms of quantum 6j6j-symbols to the volumes of deeply truncated tetrahedra.
result Supporting evidence for the conjecture in specific cases, with numerical calculations for larger dihedral angles.

We introduce neural Markov logic networks (NMLNs), a statistical relational learning system that borrows ideas from Markov logic. Like Markov logic networks (MLNs), NMLNs are an exponential-family model for modelling distributions over possible worlds, but unlike MLNs, they do not rely on explicitly specified first-ord…

2019-05-31abs ↗pdf ↗

EvoNUDGE uses graph neural networks to improve genetic programming performance.

problem Efficiency in evolutionary computation for problem solving.
method Graph neural network to elicit additional knowledge from symbolic regression problems.
result EvoNUDGE significantly outperforms conventional and neural genetic programming methods.

We show that the renormalized quantum invariants of links and graphs in the 3-sphere, derived from tensor categories in ["Modified quantum dimensions and re-normalized link invariants", arXiv:0711.4229] lead to modified 6j-symbols and to new state sum 3-manifold invariants. We give examples of categories such that the …

2009-10-08abs ↗pdf ↗

Unified approach to structured prediction combining entropy regularization and neuro-symbolic logic.

problem Structured prediction challenges due to large output spaces and insufficient labeled data.
method Neuro-symbolic entropy regularization loss that restricts entropy regularization to valid structures.
result Models predict more accurately and are more likely to be valid.

Two new methods improve graph embedding without needing a complete graph structure.

problem Graph autoencoders' performance depends on the adjacency matrix quality.
method BAGE and VBAGE: unsupervised graph embedding via adaptive graph learning.
result The methods expand GAEs' applicability to datasets without graph structure.

Graph-based approach repairs programs from diagnostic feedback.

problem Learning to repair programs from limited labeled data and compiler error messages.
method Introduces program-feedback graph and graph neural network for reasoning, and self-supervised learning with unlabeled programs.
result DrRepair significantly outperforms prior work, achieving high repair rates.