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.

169,341 papers · 148 categories

Trend · papers per month

3367100133 · May 202619922001200920182026
48 results for KB completion

New neural KB representation speeds up reasoning with large symbolic knowledge bases.

problem Efficiently reasoning with large symbolic knowledge bases.
method Sparse-matrix reified knowledge base, enabling fully differentiable, scalable neural modules.
result Competitive performance on KB completion and semantic parsing benchmarks.

New dataset and methods for inferring missing entity types in knowledge bases.

problem Inferring missing entity type instances in knowledge bases.
method Automatic evaluation methodology, uses internal KB and external Wikipedia information.
result Global objective methods outperform baseline methods in KB completion.

Develops a method for constructing KBs with tunable precision for subjective and factual attributes.

problem Complexity in measuring subjective attributes complicates precision estimation in KBs.
method Probabilistically models user consensus with respect to each entity-attribute pair, using neural networks to fit the model.
result Learned models can successfully control KB's precision and outperform baselines in attribute prediction.

BoSsNet learns language and knowledge separately, improving task-oriented dialog performance.

problem End-to-end neural networks struggle with KB changes in task-oriented dialogs.
method Encoder-decoder architecture with Bag-of-Sequences memory.
result BoSsNet outperforms state-of-the-art models with >10% improvement on bAbI OOV test sets.

Paper tackles non-stationary kernelized bandits with near-optimal algorithm.

problem Minimizing regret in a time-varying reward function.
method Near-optimal algorithm with a novel restarting phased elimination with random permutation (R-PERP).
result Regret upper bound matches the lower bound, making the algorithm near-optimal.

Efficient neural models for complex multi-hop reasoning tasks.

problem Complex multi-hop reasoning tasks in large knowledge bases.
method Differentiable neural models using symbolic knowledge bases, with a new operation for multi-hop template construction.
result Simple neural models achieve competitive performance on multi-hop reasoning tasks.

This paper tackles open problem of tight bounds for KBs with Bernoulli rewards.

problem Open problem of tight bounds for Kernelized Bandits with Bernoulli rewards.
method Focus on Bernoulli model, not subgaussian noise, and optimize function in RKHS.
result Open problem remains unsolved in this context.

Proposes OpenKI for better web-scale knowledge extraction and alignment.

problem Combining OpenIE and KB for web-scale knowledge extraction and alignment.
method Instance-level inference using neighborhood information from KB and OpenIE extractions, with attention mechanisms.
result Significantly improves performance on OpenIE extractions and semi-structured data.

We show that Sol3×E1\mathbb{S}ol^3\times\mathbb{E}^1-manifolds are Seifert fibred, with general fibre the torus, and base one of the seven flat 2-orbifolds T,Kb,A,Mb,S(2,2,2,2),P(2,2)T, Kb, \mathbb{A}, \mathbb{M}b, S(2,2,2,2), P(2,2) or D(2,2)\mathbb{D}(2,2), and outline a classification of such 4-manifolds.

2013-04-09abs ↗pdf ↗

Unified framework for simple question answering using subgraph ranking and joint-scoring.

problem Simple question answering with knowledge graphs is challenging.
method Unified framework focusing on subgraph selection and fact selection, with novel ranking and joint-scoring methods.
result Achieved state-of-the-art accuracy of 85.44% on SimpleQuestions dataset.

Improves slot key and value prediction for unseen entities.

problem Dealing with unseen slot keys and values in real-world dialogue systems.
method Leverages external knowledge bases to project slots into an attribute space and generate candidate keys and values.
result Significant improvements in F1 score and accuracy (57.7% and 82.7%, respectively) over a previous approach.

mGENRE improves multilingual entity linking with autoregressive sequence prediction.

problem Multilingual Entity Linking (MEL) task of resolving language-specific mentions to a multilingual Knowledge Base.
method Autoregressive sequence-to-sequence system that cross-encodes mention strings and entity names.
result Over 50% improvement in average accuracy in zero-shot settings.

A Kuranishi space is a topological space with a Kuranishi structure, defined by Fukaya and Ono. Kuranishi structures occur naturally on moduli spaces of J-holomorphic curves in symplectic geometry. This paper is a brief introduction to the author's book arXiv:0707.3572. Let Y be an orbifold and R a Q-algebra. We define…

2007-10-30abs ↗pdf ↗

Proposes a new method for conversational agents using deep learning.

problem Building coherent and non-monotonous conversational agents with proper discourse and coverage.
method End-to-end multi-stream deep learning architecture leveraging contextual and syntactic information.
result Significantly improved next sentence prediction task.

Generative compression technique reduces neural network size and improves performance on microcontrollers.

problem Memory constraints on microcontrollers limit the size of neural networks, especially for 1x1 pointwise (PW) mixers.
method HYPER-TINYPW uses a shared micro-MLP to generate PW kernels from tiny per-layer codes, reducing memory usage.
result HYPER-TINYPW achieves comparable performance to larger models while being significantly smaller (225 kB vs 1.4 MB).

Resource allocation improved using machine learning from terminal positions.

problem Optimizing resource allocation in next-gen wireless systems with fast-changing channel conditions.
method Supervised machine learning using position information of mobile terminals.
result Coordinates-based resource allocation performs similarly to traditional CSI-based methods.

Combines ML and KB modeling for large chaotic systems.

problem Predicting large, complex, spatiotemporal systems with limited data.
method Parallel ML prediction and hybrid approach combining ML and KB.
result Excellent performance and reduced training data needed.

FastGRNN improves RNN accuracy while drastically reducing model size.

problem Inaccurate training and inefficient prediction in RNNs.
method FastGRNN uses a residual connection and gate to achieve state-of-the-art accuracy with a much smaller model.
result FastGRNN achieves state-of-the-art accuracy with models up to 35x smaller than existing RNNs.

This paper shows that scientific discovery can be efficiently learned via compositional function trees, reducing the sample complexity.

problem Statistical and computational intractability of scientific discovery via symbolic regression.
method PAC learning approach focusing on compositional function trees built from a finite vocabulary of smooth operators.
result The Rademacher complexity and excess risk are controlled by depth and Lipschitz constants of the base operators, leading to finite-union bounds and high-probability risk bounds.

TinyBayes detects crop diseases from images on edge devices with high accuracy and minimal resources.

problem Automated disease detection for cocoa crops in resource-constrained settings.
method Combines YOLOv8-Nano for lesion localisation, MobileNetV3-Small for feature extraction, and Jacobi prior for Bayesian classification.
result Achieves 78.7% accuracy on Amini Cocoa Contamination Challenge dataset with 9.5 MB model size and 150 ms inference time.

We prove that the supergravity r- and c-maps preserve completeness. As a consequence, any component H of a hypersurface {h=1} defined by a homogeneous cubic polynomial such that -d^2 h is a complete Riemannian metric on H defines a complete projective special Kahler manifold and any complete projective special Kahler m…

2011-01-26abs ↗pdf ↗

New invariant defined for complete and bipartite graphs, determining Thurston-Bennequin numbers.

problem Determining Thurston-Bennequin numbers for complete and bipartite Legendrian graphs.
method Defined a total Thurston-Bennequin number, showed its determination by 3-cycles for complete graphs and 4-cycles for bipartite graphs.
result The total Thurston-Bennequin number is a new invariant that determines Thurston-Bennequin numbers for complete and bipartite graphs.

The paper classifies 2D complete λλ-surfaces in 3D space.

problem Classifying complete λλ-surfaces in R3\mathbb R^3.
method Complete classification of 2D complete λλ-surfaces with constant squared norm of the second fundamental form.
result A complete classification for 2-dimensional complete λλ-surfaces in Euclidean space R3\mathbb R^3 with constant squared norm of the second fundamental form.

Study geodesic and affine Killing completeness in homogeneous affine surfaces.

problem Geodesic and affine Killing completeness in homogeneous affine surfaces.
method Examined using the solution space of the quasi-Einstein equation.
result Characterized geodesic and affine Killing completeness in homogeneous affine surfaces.

Study directed completion of spacetimes, focusing on Schwarzschild spacetime.

problem Characterizing directed completions of spacetimes.
method Directed completion of Lorentzian pre-length spaces, focusing on Schwarzschild spacetime.
result Directed completion of Schwarzschild spacetime coincides with future causal completion.

Completeness of surface metrics established for Sobolev spaces.

problem Ensuring completeness of reparametrization-invariant Sobolev metrics on surface spaces.
method Recasting completeness criteria for infinite-dimensional Riemannian manifolds and applying geometric estimates based on the Michael--Simon--Sobolev inequality.
result Established metric and geodesic completeness for specific Sobolev metrics on immersed surfaces, validating Mumford's conjecture.

The study classifies complete Lagrangian self-shrinkers in 4D space.

problem Classifying complete Lagrangian self-shrinkers in 4D space.
method Complete classification of 2D complete Lagrangian self-shrinkers with constant squared norm of the second fundamental form.
result A complete classification for 2-dimensional complete Lagrangian self-shrinkers in R4\mathbf R^4 with constant squared norm of the second fundamental form.

Incomplete markets are statistically indistinguishable from complete ones.

problem Statistical evaluation of market completeness under uncertainty.
method Investigation of discrete time stock market models, showing incompleteness is non-robust.
result Incomplete markets are statistically equivalent to complete ones.

Study disproves conjecture about metric completion of curve spaces.

problem Completeness properties of spaces of immersed curves with reparametrization-invariant metrics.
method Examined Sobolev-type metrics on real-valued immersed curves, demonstrating multiple distinct limit points.
result Metric completion of spaces of immersed open curves includes multiple distinct limit points, not a single point as previously conjectured.

Polyhedral semantics for intermediate logics; Nerve Criterion ensures completeness.

problem Characterize polyhedrally-complete intermediate logics.
method Developed Nerve Criterion to characterize polyhedrally-complete logics combinatorially.
result Nerve Criterion provides a necessary and sufficient condition for polyhedrally-completeness.