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.
New algorithms detect outliers in high-dimensional data with arbitrary shapes.
We find the maximum mutual information for neural networks and its key determinants.
Two new outlyingness scores improve outlier detection in high-dimensional data.
A new graph-based clustering method for moderate-dimensional data.
Graph cuts find global optima for Potts models in slight perturbations.
This paper proposes a method to learn graph representations without supervision.
A novel method integrates feature and topology views for unsupervised graph representation learning.
A variety of graph neural networks (GNNs) frameworks for representation learning on graphs have been recently developed. These frameworks rely on aggregation and iteration scheme to learn the representation of nodes. However, information between nodes is inevitably lost in the scheme during learning. In order to reduce…
A novel algorithm for unsupervised graph representation learning combining coarsening and mutual information maximization.
A drone catches another agile drone using competitive reinforcement learning.
Unsupervised method learns hierarchical graph representations without labels.
Graph Information Bottleneck (GIB) optimizes graph representations for robustness against adversarial attacks.
A new method identifies similar mutual funds using graph learning.
Proposes GIB for recognizing informative subgraphs in graphs.
Mutual teaching improves graph models with less labeled data.
Using an inverse system of metric graphs as in: J. Cheeger and B. Kleiner, "Inverse limit spaces satisfying a Poincaré inequality", we provide a simple example of a metric space that admits Poincaré inequalities for a continuum of mutually singular measures.
Proposes a method to select features for subgroup datasets with systematic missing data.
Some explanations to Kaldi's PLDA implementation to make formula derivation easier to catch.
Spatio-temporal graphs such as traffic networks or gene regulatory systems present challenges for the existing deep learning methods due to the complexity of structural changes over time. To address these issues, we introduce Spatio-Temporal Deep Graph Infomax (STDGI)---a fully unsupervised node representation learning…
MEG models for dynamic networks estimate dependencies and shared latent space relationships.
This paper studies learning the representations of whole graphs in both unsupervised and semi-supervised scenarios. Graph-level representations are critical in a variety of real-world applications such as predicting the properties of molecules and community analysis in social networks. Traditional graph kernel based me…
LambdaNet infers TypeScript types using graph neural networks.
This paper resolves the all-or-nothing phase transition in graph matching.
Learning to cooperate is crucially important in multi-agent environments. The key is to understand the mutual interplay between agents. However, multi-agent environments are highly dynamic, where agents keep moving and their neighbors change quickly. This makes it hard to learn abstract representations of mutual interp…
This paper analyzes popular time-nonseparable utility functions that describe "habit formation" consumer preferences comparing current consumption with the time averaged past consumption of the same individual and "catching up with the Joneses" (CuJ) models comparing individual consumption with a cross-sectional averag…
We propose clustering algorithms based on a recently developed geometric digraph family called cluster catch digraphs (CCDs). These digraphs are used to devise clustering methods that are hybrids of density-based and graph-based clustering methods. CCDs are appealing digraphs for clustering, since they estimate the num…
New method optimizes hierarchical multi-label classification results.
While a wide range of interpretable generative procedures for graphs exist, matching observed graph topologies with such procedures and choices for its parameters remains an open problem. Devising generative models that closely reproduce real-world graphs requires domain knowledge and time-consuming simulation. While e…
New framework optimizes deep learning training by deferring large batch sizes to late stages.
Proposes VCLANC for attributed network clustering using node and attribute embeddings.
We study the market selection hypothesis in complete financial markets, populated by heterogeneous agents. We allow for a rich structure of heterogeneity: individuals may differ in their beliefs concerning the economy, information and learning mechanism, risk aversion, impatience and 'catching up with Joneses' preferen…
We study clustering algorithms based on neighborhood graphs on a random sample of data points. The question we ask is how such a graph should be constructed in order to obtain optimal clustering results. Which type of neighborhood graph should one choose, mutual k-nearest neighbor or symmetric k-nearest neighbor? What …
Graph cross network improves graph classification accuracy.
Proposes an unsupervised graph neural network for entire graph representation.
CGRL improves graph neural networks' OOD generalization by blocking spurious correlations.
The interactions of users and items in recommender system could be naturally modeled as a user-item bipartite graph. In recent years, we have witnessed an emerging research effort in exploring user-item graph for collaborative filtering methods. Nevertheless, the formation of user-item interactions typically arises fro…
The econophysics approach to socio-economic systems is based on the assumption of their complexity. Such assumption inevitably lead to another assumption, namely that underlying interconnections within socio-economic systems, particularly financial markets, are nonlinear, which is shown to be true even in mainstream ec…
We present simple and computationally efficient nonparametric estimators of Rényi entropy and mutual information based on an i.i.d. sample drawn from an unknown, absolutely continuous distribution over . The estimators are calculated as the sum of -th powers of the Euclidean lengths of the edges of the `genera…
Graph Neural Networks (GNNs) achieve an impressive performance on structured graphs by recursively updating the representation vector of each node based on its neighbors, during which parameterized transformation matrices should be learned for the node feature updating. However, existing propagation schemes are far fro…
The paper introduces submodular information measures for machine learning applications.
GAttNHP predicts future events in temporal knowledge graphs by encoding long-range dependencies and handling mutual excitation.
Enhances graph modeling with hyperbolic geometry and variational inference.
We employ random geometric digraphs to construct semi-parametric classifiers. These data-random digraphs are from parametrized random digraph families called proximity catch digraphs (PCDs). A related geometric digraph family, class cover catch digraph (CCCD), has been used to solve the class cover problem by using its…
We consider the problem of estimating the underlying graph associated with a Markov random field, with the added twist that the decoding algorithm can iteratively choose which subsets of nodes to sample based on the previous samples, resulting in an active learning setting. Considering both Ising and Gaussian models, w…
The paper establishes bounds for transductive learning using information theory.
Bayesian Algorithm Execution uses mutual information to infer properties of black-box functions efficiently.
We propose a method for learning Markov network structures for continuous data without invoking any assumptions about the distribution of the variables. The method makes use of previous work on a non-parametric estimator for mutual information which is used to create a non-parametric test for multivariate conditional i…
We present Deep Graph Infomax (DGI), a general approach for learning node representations within graph-structured data in an unsupervised manner. DGI relies on maximizing mutual information between patch representations and corresponding high-level summaries of graphs---both derived using established graph convolutiona…