Search Results for author:
Found 17 papers, 10 papers with code
Discrete Neural Algorithmic Reasoning
Neural algorithmic reasoning aims to capture computations with neural networks via learning the models to imitate the execution of classical algorithms.
A critical look at the evaluation of GNNs under heterophily: Are we really making progress?
Graphs without this property are called heterophilous, and it is typically assumed that specialized methods are required to achieve strong performance on such graphs.
Characterizing Graph Datasets for Node Classification: Homophily-Heterophily Dichotomy and Beyond
For this, we formalize desirable properties for a proper homophily measure and verify which measures satisfy which properties.
Gradient Boosting Performs Gaussian Process Inference
Thus, we obtain the convergence to a Gaussian Process' posterior mean, which, in turn, allows us to easily transform gradient boosting into a sampler from the posterior to provide better knowledge uncertainty estimates through Monte-Carlo estimation of the posterior variance.
Which Tricks Are Important for Learning to Rank?
To address these questions, we compare LambdaMART with YetiRank and StochasticRank methods and their modifications.
Good Classification Measures and How to Find Them
Several performance measures can be used for evaluating classification results: accuracy, F-measure, and many others.
Graph-based Nearest Neighbor Search in Hyperbolic Spaces
From a theoretical perspective, we rigorously analyze the time and space complexity of graph-based NNS, assuming that an n-element dataset is uniformly distributed within a d-dimensional ball of radius R in the hyperbolic space of curvature -1.
Shifts: A Dataset of Real Distributional Shift Across Multiple Large-Scale Tasks
However, many tasks of practical interest have different modalities, such as tabular data, audio, text, or sensor data, which offer significant challenges involving regression and discrete or continuous structured prediction.
Ranked #2 on
Weather Forecasting
on Shifts
Boost then Convolve: Gradient Boosting Meets Graph Neural Networks
Previous GNN models have mostly focused on networks with homogeneous sparse features and, as we show, are suboptimal in the heterogeneous setting.
Embedding Words in Non-Vector Space with Unsupervised Graph Learning
We adopt a recent method learning a representation of data in the form of a differentiable weighted graph and use it to modify the GloVe training algorithm.
Overlapping Spaces for Compact Graph Representations
We generalize the concept of product space and introduce an overlapping space that does not have the configuration search problem.
Uncertainty in Gradient Boosting via Ensembles
For many practical, high-risk applications, it is essential to quantify uncertainty in a model's predictions to avoid costly mistakes.
StochasticRank: Global Optimization of Scale-Free Discrete Functions
The problem is ill-posed due to the discrete structure of the loss, and to deal with that, we introduce two important techniques: stochastic smoothing and novel gradient estimate based on partial integration.
SGLB: Stochastic Gradient Langevin Boosting
This paper introduces Stochastic Gradient Langevin Boosting (SGLB) - a powerful and efficient machine learning framework that may deal with a wide range of loss functions and has provable generalization guarantees.
Global graph curvature
We show that optimal curvature essentially depends on dimensionality of the embedding space and loss function one aims to minimize via embedding.
Graph-based Nearest Neighbor Search: From Practice to Theory
Graph-based approaches are empirically shown to be very successful for the nearest neighbor search (NNS).
Data Structures and Algorithms Probability
CatBoost: unbiased boosting with categorical features
This paper presents the key algorithmic techniques behind CatBoost, a new gradient boosting toolkit.
