arXiv research

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

A new query embedding method improves KB performance on complex queries.

The Knowledge Base (KB) used for real-world applications, such as booking a movie or restaurant reservation, keeps changing over time. End-to-end neural networks trained for these task-oriented dialogs are expected to be immune to any changes in the KB. However, existing approaches breakdown when asked to handle such c…

Knowledge bases (KBs) are the backbone of many ubiquitous applications and are thus required to exhibit high precision. However, for KBs that store subjective attributes of entities, e.g., whether a movie is "kid friendly", simply estimating precision is complicated by the inherent ambiguity in measuring subjective phe…

Solves TOD systems' query annotation problem without explicit annotations.

We present efficient differentiable implementations of second-order multi-hop reasoning using a large symbolic knowledge base (KB). We introduce a new operation which can be used to compositionally construct second-order multi-hop templates in a neural model, and evaluate a number of alternative implementations, with d…

Given a knowledge base or KB containing (noisy) facts about common nouns or generics, such as "all trees produce oxygen" or "some animals live in forests", we consider the problem of inferring additional such facts at a precision similar to that of the starting KB. Such KBs capture general knowledge about the world, an…

Proposes a new PBO method with theoretical guarantees.

Most of previous work in knowledge base (KB) completion has focused on the problem of relation extraction. In this work, we focus on the task of inferring missing entity type instances in a KB, a fundamental task for KB competition yet receives little attention. Due to the novelty of this task, we construct a large-sca…

Knowledge base (KB) completion adds new facts to a KB by making inferences from existing facts, for example by inferring with high likelihood nationality(X,Y) from bornIn(X,Y). Most previous methods infer simple one-hop relational synonyms like this, or use as evidence a multi-hop relational path treated as an atomic f…

Dealing with previously unseen slots is a challenging problem in a real-world multi-domain dialogue state tracking task. Other approaches rely on predefined mappings to generate candidate slot keys, as well as their associated values. This, however, may fail when the key, the value, or both, are not seen during trainin…

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

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

We study the regret minimization problem in the novel setting of generalized kernelized bandits (GKBs), where we optimize an unknown function $f^*$ belonging to a reproducing kernel Hilbert space (RKHS) having access to samples generated by an exponential family (EF) reward model whose mean is a non-linear function $μ(…

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

Knowledge graph based simple question answering (KBSQA) is a major area of research within question answering. Although only dealing with simple questions, i.e., questions that can be answered through a single knowledge base (KB) fact, this task is neither simple nor close to being solved. Targeting on the two main ste…

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

In this paper, we consider advancing web-scale knowledge extraction and alignment by integrating OpenIE extractions in the form of (subject, predicate, object) triples with Knowledge Bases (KB). Traditional techniques from universal schema and from schema mapping fall in two extremes: either they perform instance-level…

mGENRE improves multilingual entity linking with autoregressive sequence prediction.

Training-free source selection for LLM families with shared vocabularies

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…

This paper develops the FastRNN and FastGRNN algorithms to address the twin RNN limitations of inaccurate training and inefficient prediction. Previous approaches have improved accuracy at the expense of prediction costs making them infeasible for resource-constrained and real-time applications. Unitary RNNs have incre…

The problem of building a coherent and non-monotonous conversational agent with proper discourse and coverage is still an area of open research. Current architectures only take care of semantic and contextual information for a given query and fail to completely account for syntactic and external knowledge which are cru…

Resource allocation improved using machine learning from terminal positions.

Combines ML and KB modeling for large chaotic systems.

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

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

Graphs of neural networks are represented to preserve symmetry, improving performance across various tasks.

Convolutional Neural Processes improve data efficiency in neural processes.

Neural Ordinary Differential Equation (Neural ODE) has been proposed as a continuous approximation to the ResNet architecture. Some commonly used regularization mechanisms in discrete neural networks (e.g. dropout, Gaussian noise) are missing in current Neural ODE networks. In this paper, we propose a new continuous ne…

Investigates how neural network graph structure impacts predictive performance.

Novel framework explains generalization in deep neural networks.

Neural networks can approximate functions uniformly across various measures.

Investigates neural codes and their embeddings, proving conjectures and introducing new code types.

Neural dynamical systems are dynamical systems that are described at least in part by neural networks. The class of continuous-time neural dynamical systems must, however, be numerically integrated for simulation and learning. Here, we present a compact neural circuit for two common numerical integrators: the explicit …

Quadratic models explain neural network behavior during training.

Graph Metanetworks process diverse neural architectures efficiently.

Optimal rates for shallow ReLU networks in nonparametric regression.

New metric compares noisy neural trajectories using optimal transport.

The neural tangent kernel equivalence theorem fails in practice.

Equivariant neural networks use symmetry to interpret complex data.

Two new criteria help understand the advantage of deep neural networks.

Use simplified layerwise linear models to understand neural dynamics.

Analysis of over-parameterized neural networks has drawn significant attention in recentyears. It was shown that such systems behave like convex systems under various restrictedsettings, such as for two-level neural networks, and when learning is only restricted locally inthe so-called neural tangent kernel space aroun…

The paper proves consistency of neural networks with regularization.

This study shows why training Neural ODEs is hard and proposes a new method.

We introduce Graph Neural Processes (GNP), inspired by the recent work in conditional and latent neural processes. A Graph Neural Process is defined as a Conditional Neural Process that operates on arbitrary graph data. It takes features of sparsely observed context points as input, and outputs a distribution over targ…

Paper benchmarks quantum neural networks against classical ones for binary classification tasks.