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.
Method generates time-series attribution maps with identifiability guarantees.
Study uncovers bias in image classification models using attribution maps.
Improved 3D ECG feature attributions for clinical interpretation.
Improved saliency maps for deep neural networks with reduced noise.
Existing techniques to compress point cloud attributes leverage either geometric or video-based compression tools. We explore a radically different approach inspired by recent advances in point cloud representation learning. Point clouds can be interpreted as 2D manifolds in 3D space. Specifically, we fold a 2D grid on…
In many graphs such as social networks, nodes have associated attributes representing their behavior. Predicting node attributes in such graphs is an important problem with applications in many domains like recommendation systems, privacy preservation, and targeted advertisement. Attributes values can be predicted by a…
WassersteinGrad improves weather forecasting explanations by addressing geometric misalignment issues.
In this paper, we study the problem of transfer learning with the attribute data. In the transfer learning problem, we want to leverage the data of the auxiliary and the target domains to build an effective model for the classification problem in the target domain. Meanwhile, the attributes are naturally stable cross d…
ICAM creates interpretable feature attribution maps for brain images.
Concept Relation Discovery and Innovation Enabling Technology (CORDIET), is a toolbox for gaining new knowledge from unstructured text data. At the core of CORDIET is the C-K theory which captures the essential elements of innovation. The tool uses Formal Concept Analysis (FCA), Emergent Self Organizing Maps (ESOM) and…
New method separates graph structure from node attributes to recover lost signal.
Paper tackles target shift in zero-shot learning using adversarial learning.
DFI maps covariates to latent representations for feature importance.
New method makes CNN interpretations robust to adversarial attacks.
Paper tackles source attribution for LLM-generated texts.
Saliency methods can aid understanding of deep neural networks. Recent years have witnessed many improvements to saliency methods, as well as new ways for evaluating them. In this paper, we 1) present a novel region-based attribution method, XRAI, that builds upon integrated gradients (Sundararajan et al. 2017), 2) int…
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…
Proposes fair mapping to prevent bias in model predictions without distorting data.
We propose graph kernels based on subgraph matchings, i.e. structure-preserving bijections between subgraphs. While recently proposed kernels based on common subgraphs (Wale et al., 2008; Shervashidze et al., 2009) in general can not be applied to attributed graphs, our approach allows to rate mappings of subgraphs by …
A barrier to the wider adoption of neural networks is their lack of interpretability. While local explanation methods exist for one prediction, most global attributions still reduce neural network decisions to a single set of features. In response, we present an approach for generating global attributions called GAM, w…
Semi-Non-negative Matrix Factorization is a technique that learns a low-dimensional representation of a dataset that lends itself to a clustering interpretation. It is possible that the mapping between this new representation and our original data matrix contains rather complex hierarchical information with implicit lo…
Local decision boundary approximation improves model explanations for complex models.
Attribution methods provide insights into the decision-making of machine learning models like artificial neural networks. For a given input sample, they assign a relevance score to each individual input variable, such as the pixels of an image. In this work we adapt the information bottleneck concept for attribution. B…
Zero-shot learning (ZSL) is a framework to classify images belonging to unseen classes based on solely semantic information about these unseen classes. In this paper, we propose a new ZSL algorithm using coupled dictionary learning. The core idea is that the visual features and the semantic attributes of an image can s…
Feature attribution methods, or saliency maps, are one of the most popular approaches for explaining the decisions of complex machine learning models such as deep neural networks. In this study, we propose a stochastic optimization approach for the perturbation-based feature attribution method. While the original optim…
We consider analysis of relational data (a matrix), in which the rows correspond to subjects (e.g., people) and the columns correspond to attributes. The elements of the matrix may be a mix of real and categorical. Each subject and attribute is characterized by a latent binary feature vector, and an inferred matrix map…
Unified bounds for DP risks reduce noise and improve accuracy.
In this paper we explore the applicability of the unsupervised machine learning technique of Self Organizing Maps (SOM) to estimate galaxy photometric redshift probability density functions (PDFs). This technique takes a spectroscopic training set, and maps the photometric attributes, but not the redshifts, to a two di…
AP-Calculus offers a new framework for causal inference in Bayesian networks.
Unified framework for linear attribution methods in deep learning.
ZegOT uses optimal transport to zero-shot segment images with text prompts.
Saliency Map, the gradient of the score function with respect to the input, is the most basic technique for interpreting deep neural network decisions. However, saliency maps are often visually noisy. Although several hypotheses were proposed to account for this phenomenon, there are few works that provide rigorous ana…
Extends local attributions to Bayesian Neural Networks for improved explanations.
Interpretability and fairness are critical in computer vision and machine learning applications, in particular when dealing with human outcomes, e.g. inviting or not inviting for a job interview based on application materials that may include photographs. One promising direction to achieve fairness is by learning data …
This paper explores BDL hyperparameters for robust polynomial mapping with noise.
Post-hoc explanations improve CNNs by replacing final linear layer with k-means classifier.
Computer-aided diagnosis systems for classification of different type of skin lesions have been an active field of research in recent decades. It has been shown that introducing lesions and their attributes masks into lesion classification pipeline can greatly improve the performance. In this paper, we propose a framew…
Aggregate network properties such as cluster cohesion and the number of bridge nodes can be used to glean insights about a network's community structure, spread of influence and the resilience of the network to faults. Efficiently computing network properties when the network is fully observed has received significant …
Study evaluates deep learning models for solar flare prediction with interpretability analysis.
Layer-wise Relevance Propagation (LRP) and saliency maps have been recently used to explain the predictions of Deep Learning models, specifically in the domain of text classification. Given different attribution-based explanations to highlight relevant words for a predicted class label, experiments based on word deleti…
This paper presents a Semantic Attribute Modulation (SAM) for language modeling and style variation. The semantic attribute modulation includes various document attributes, such as titles, authors, and document categories. We consider two types of attributes, (title attributes and category attributes), and a flexible a…
Let N^h be a hyperbolic 3-manifold of bounded geometry corresponding to a hyperbolic structure on a pared manifold (M,P). Further, suppose that (\partial{M} - P) is incompressible, i.e. the boundary of M is incompressible away from cusps. Further, suppose that M_{gf} is a geometrically finite hyperbolic structure on (M…
MOPI optimizes flexible set-valued mappings to achieve superior shape adaptivity in conformal prediction.
NN-EVCLUS uses neural networks to cluster data with uncertainty.
Traditional disease surveillance can be augmented with a wide variety of real-time sources such as, news and social media. However, these sources are in general unstructured and, construction of surveillance tools such as taxonomical correlations and trace mapping involves considerable human supervision. In this paper,…
Proposes a Taylor framework to unify and analyze attribution methods.
Unified framework for analyzing machine learning model attributions.
MAPPING debiases GNNs for fair node classification with limited leakage.