arXiv subjects

Daniel Gonzalez Cedre

Publications and source records attributed to Daniel Gonzalez Cedre.

7 recordsLinked to original sources

arXiv2024

This Probably Looks Exactly Like That: An Invertible Prototypical Network

We combine concept-based neural networks with generative, flow-based classifiers into a novel, intrinsically explainable, exactly invertible approach to supervised learning. Prototypical neural networks, a type of concept-based neural network, represent an exciting way forward in realizing human-comprehensible machine learning without concept annotations, but a human-machine semantic gap continues to haunt current approaches. We find that reliance on indirect interpretation functions for prototypical explanations imposes a severe limit on prototypes' informative power. From this, we posit that invertibly learning prototypes as distributions over the latent space provides more robust, expressive, and interpretable modeling. We propose one such model, called ProtoFlow, by composing a normalizing flow with Gaussian mixture models. ProtoFlow (1) sets a new state-of-the-art in joint generative and predictive modeling and (2) achieves predictive performance comparable to existing prototypical neural networks while enabling richer interpretation.

cs.LG↗

arXiv2023

Temporal Egonet Subgraph Transitions

How do we summarize dynamic behavioral interactions? We introduce a possible node-embedding-based solution to this question: temporal egonet subgraph transitions.

cs.SI↗

arXiv2023

Dynamic Vertex Replacement Grammars

Context-free graph grammars have shown a remarkable ability to model structures in real-world relational data. However, graph grammars lack the ability to capture time-changing phenomena since the left-to-right transitions of a production rule do not represent temporal change. In the present work, we describe dynamic vertex-replacement grammars (DyVeRG), which generalize vertex replacement grammars in the time domain by providing a formal framework for updating a learned graph grammar in accordance with modifications to its underlying data. We show that DyVeRG grammars can be learned from, and used to generate, real-world dynamic graphs faithfully while remaining human-interpretable. We also demonstrate their ability to forecast by computing dyvergence scores, a novel graph similarity measurement exposed by this framework.

cs.LG↗

arXiv2022

Motif Mining: Finding and Summarizing Remixed Image Content

On the internet, images are no longer static; they have become dynamic content. Thanks to the availability of smartphones with cameras and easy-to-use editing software, images can be remixed (i.e., redacted, edited, and recombined with other content) on-the-fly and with a world-wide audience that can repeat the process. From digital art to memes, the evolution of images through time is now an important topic of study for digital humanists, social scientists, and media forensics specialists. However, because typical data sets in computer vision are composed of static content, the development of automated algorithms to analyze remixed content has been limited. In this paper, we introduce the idea of Motif Mining - the process of finding and summarizing remixed image content in large collections of unlabeled and unsorted data. In this paper, this idea is formalized and a reference implementation is introduced. Experiments are conducted on three meme-style data sets, including a newly collected set associated with the information war in the Russo-Ukrainian conflict. The proposed motif mining approach is able to identify related remixed content that, when compared to similar approaches, more closely aligns with the preferences and expectations of human observers.

cs.CV↗

arXiv2022

Joint Subgraph-to-Subgraph Transitions -- Generalizing Triadic Closure for Powerful and Interpretable Graph Modeling

We generalize triadic closure, along with previous generalizations of triadic closure, under an intuitive umbrella generalization: the Subgraph-to-Subgraph Transition (SST). We present algorithms and code to model graph evolution in terms of collections of these SSTs. We then use the SST framework to create link prediction models for both static and temporal, directed and undirected graphs which produce highly interpretable results. Quantitatively, our models match out-of-the-box performance of state of the art graph neural network models, thereby validating the correctness and meaningfulness of our interpretable results.

cs.SI↗

arXiv2022

Monotone Catenary Degree in Numerical Monoids

Recent investigations on the catenary degrees of numerical monoids have demonstrated that this invariant is a powerful tool in understanding the factorization theory of this class of monoids. Although useful, the catenary degree is largely not sensitive to the lengths of factorizations of an element. In this paper, we study the monotone catenary degree of numerical monoids, which is a variant of catenary degree that requires chains run through factorization lengths monotonically. In general, the monotone catenary is greater than or equal to the catenary degree. We begin by providing an important class of monoids (arithmetical numerical monoids) for which monotone catenary degree is equal to the catenary degree. Conversely, we provide several classes of embedding dimension 3 numerical monoids where monotone catenary degree is strictly greater. We conclude by showing that this difference can grow arbitrarily large.

math.AC↗

arXiv2022

The Infinity Mirror Test for Graph Models

Graph models, like other machine learning models, have implicit and explicit biases built-in, which often impact performance in nontrivial ways. The model's faithfulness is often measured by comparing the newly generated graph against the source graph using any number or combination of graph properties. Differences in the size or topology of the generated graph, therefore, indicate a loss in the model. Yet, in many systems, errors encoded in loss functions are subtle and not well understood. In the present work, we introduce the Infinity Mirror test for analyzing the robustness of graph models. This straightforward stress test works by repeatedly fitting a model to its own outputs. A hypothetically perfect graph model would have no deviation from the source graph; however, the model's implicit biases and assumptions are exaggerated by the Infinity Mirror test, exposing potential issues that were previously obscured. Through an analysis of thousands of experiments on synthetic and real-world graphs, we show that several conventional graph models degenerate in exciting and informative ways. We believe that the observed degenerative patterns are clues to the future development of better graph models.

cs.SI↗