arXiv research

Paper investigates neural query graph ranking for complex question answering over knowledge graphs.

Attention improves edge prediction in e-commerce graphs.

Proposes a new query autocompletion method that maximizes retrieval performance.

Retrieving the most similar objects in a large-scale database for a given query is a fundamental building block in many application domains, ranging from web searches, visual, cross media, and document retrievals. State-of-the-art approaches have mainly focused on capturing the underlying geometry of the data manifolds…

Distributions over rankings are used to model data in various settings such as preference analysis and political elections. The factorial size of the space of rankings, however, typically forces one to make structural assumptions, such as smoothness, sparsity, or probabilistic independence about these underlying distri…

New methods improve graph classification accuracy using regional uncertainty.

A method for ranking items using distance-based learning from positive and unlabeled data.

Algorithm learns diverse rankings for search engines.

InfoTuple efficiently selects larger tuple queries for ranking multiple objects, improving efficiency and consistency.

Proposes CGA model for logical queries over KGs.

Study efficient graph optimization with noisy data.

We investigate the problem of active learning on a given tree whose nodes are assigned binary labels in an adversarial way. Inspired by recent results by Guillory and Bilmes, we characterize (up to constant factors) the optimal placement of queries so to minimize the mistakes made on the non-queried nodes. Our query se…

This paper explores the adaptive (active) PAC (probably approximately correct) top-$k$ ranking (i.e., top-$k$ item selection) and total ranking problems from $l$-wise ($l\geq 2$) comparisons under the multinomial logit (MNL) model. By adaptively choosing sets to query and observing the noisy output of the most favored …

New method recovers graph structure from covariance queries efficiently.

MarlRank uses multi-agent reinforcement learning to improve document ranking.

New algorithm tackles dynamic query routing to multiple embedding models.

The problem of searching for experts in a given academic field is hugely important in both industry and academia. We study exactly this issue with respect to a database of authors and their publications. The idea is to use Latent Semantic Indexing (LSI) and Latent Dirichlet Allocation (LDA) to perform topic modelling i…

LITE models improve query-document relevance with learnable late interactions.

We model GitHub interactions as a temporal knowledge graph for software engineering questions.

Improves node classification in graphs with active learning.

Improved algorithm for selecting a hypothesis locally privately with fewer queries.

New method uses low logit rank to simplify complex language models.

Study exact community recovery in noisy SBM with limited queries.

Paper builds LETOR models for e-commerce, segmenting queries and optimizing search results.

A new hypergraph-based active learning scheme reduces query complexity.

A new perceptual adjustment query for metric learning reduces complexity in high-dimensional data.

This paper improves nearest neighbor search by learning optimal routing functions.

Optimizes functions on manifolds using Gaussian processes and graph models.

Path queries on a knowledge graph can be used to answer compositional questions such as "What languages are spoken by people living in Lisbon?". However, knowledge graphs often have missing facts (edges) which disrupts path queries. Recent models for knowledge base completion impute missing facts by embedding knowledge…

Query2box embeds complex queries as boxes to handle logical operations in large KGs.

LSDAT reduces query efficiency for decision-based adversarial attacks.

The paper tests properties of trees in graphical models using covariance queries.

Proposes an offline active learning method for graphs.

NeuroMatch efficiently matches subgraphs in large graphs using neural networks.

Paper learns Erdős-Rényi graphs with few queries.

Graph embedding provides an efficient solution for graph analysis by converting the graph into a low-dimensional space which preserves the structure information. In contrast to the graph structure data, the i.i.d. node embedding can be processed efficiently in terms of both time and space. Current semi-supervised graph…

VACA models graph data for causal inference without hidden confounders.

Ricci-Filtration enhances retrieval-augmented generation rerankers for query-answer tasks by using discrete Ricci flow on graphs.

Learning low-dimensional embeddings of knowledge graphs is a powerful approach used to predict unobserved or missing edges between entities. However, an open challenge in this area is developing techniques that can go beyond simple edge prediction and handle more complex logical queries, which might involve multiple un…

We show that for the problem of testing if a matrix $A \in F^{n \times n}$ has rank at most $d$, or requires changing an $ε$-fraction of entries to have rank at most $d$, there is a non-adaptive query algorithm making $\widetilde{O}(d^2/ε)$ queries. Our algorithm works for any field $F$. This improves upon the previous…

A new method reduces inference cost for FwFM by allowing it to scale with item fields only.

Most content-based image retrieval systems consider either one single query, or multiple queries that include the same object or represent the same semantic information. In this paper we consider the content-based image retrieval problem for multiple query images corresponding to different image semantics. We propose a…

Proposes a graph-based method for active learning in regression.

GraphQ system uses GNNs to search for subgraph patterns in graphs.

The problem of active diagnosis arises in several applications such as disease diagnosis, and fault diagnosis in computer networks, where the goal is to rapidly identify the binary states of a set of objects (e.g., faulty or working) by sequentially selecting, and observing, (noisy) responses to binary valued queries. …

Bayesian optimisation method targets graph classification models against adversarial attacks.

Algorithm learns nearest neighbor graph from noisy distance queries.

Paper studies model stealing for low-rank language models.