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.
Unified framework for analyzing machine learning model attributions.
Proposes VCLANC for attributed network clustering using node and attribute embeddings.
New method separates graph structure from node attributes to recover lost signal.
A new method improves semi-supervised learning by handling tasks with different attribute spaces.
Mining tasks over sequential data, such as clickstreams and gene sequences, require a careful design of embeddings usable by learning algorithms. Recent research in feature learning has been extended to sequential data, where each instance consists of a sequence of heterogeneous items with a variable length. However, m…
Anomaly detection on attributed networks aims at finding nodes whose patterns deviate significantly from the majority of reference nodes, which is pervasive in many applications such as network intrusion detection and social spammer detection. However, most existing methods neglect the complex cross-modality interactio…
Method generates time-series attribution maps with identifiability guarantees.
Framework learns dynamic graph attributes and links co-evolution.
MAIN network learns attributes without unseen class attributes for faster, more adaptable ZSL.
Proposes a Taylor framework to unify and analyze attribution methods.
RoSHAP stabilizes feature attribution in machine learning models.
Recent research has demonstrated that feature attribution methods for deep networks can themselves be incorporated into training; these attribution priors optimize for a model whose attributions have certain desirable properties -- most frequently, that particular features are important or unimportant. These attributio…
This paper presents the Variation Network (VarNet), a generative model providing means to manipulate the high-level attributes of a given input. The originality of our approach is that VarNet is not only capable of handling pre-defined attributes but can also learn the relevant attributes of the dataset by itself. Thes…
Unified analysis of removal-based feature attributions robustness.
Structured latent attribute models (SLAMs) are a special family of discrete latent variable models widely used in social and biological sciences. This paper considers the problem of learning significant attribute patterns from a SLAM with potentially high-dimensional configurations of the latent attributes. We address …
Recent work has explored how to train machine learning models which do not discriminate against any subgroup of the population as determined by sensitive attributes such as gender or race. To avoid disparate treatment, sensitive attributes should not be considered. On the other hand, in order to avoid disparate impact,…
Adapts IG for better feature attributions and robustness.
New method learns fair representations by separating out protected attributes.
DRSVM uses deep learning to rank relative attributes between image pairs.
Facial attribute editing aims to manipulate single or multiple attributes of a face image, i.e., to generate a new face with desired attributes while preserving other details. Recently, generative adversarial net (GAN) and encoder-decoder architecture are usually incorporated to handle this task with promising results.…
Graph structured data provide two-fold information: graph structures and node attributes. Numerous graph-based algorithms rely on both information to achieve success in supervised tasks, such as node classification and link prediction. However, node attributes could be missing or incomplete, which significantly deterio…
MACQ method explains deep learning models by analyzing feature contributions across prediction levels.
We explore a new domain of learning to infer user interface attributes that helps developers automate the process of user interface implementation. Concretely, given an input image created by a designer, we learn to infer its implementation which when rendered, looks visually the same as the input image. To achieve thi…
Introduces FairCOCCO for fair learning with multitype, multivariate sensitive attributes.
SLOGAN improves GANs' conditional generation by balancing latent attribute distributions.
Study reveals attributes help in few-shot classification generalization.
Greedy PIG adapts integrated gradients for better feature attribution.
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…
This research compares two encoding methods for categorical attributes in machine learning, affecting model fairness.
GGDA simplifies DA for large models, speeding up attribution by up to 50x.
This work introduces a fair learning method for diverse sensitive attributes.
In this paper, we present a novel attack against authorship attribution of source code. We exploit that recent attribution methods rest on machine learning and thus can be deceived by adversarial examples of source code. Our attack performs a series of semantics-preserving code transformations that mislead learning-bas…
WGNN learns graph representations from incomplete attribute data.
In many networks, vertices have hidden attributes, or types, that are correlated with the networks topology. If the topology is known but these attributes are not, and if learning the attributes is costly, we need a method for choosing which vertex to query in order to learn as much as possible about the attributes of …
Generic generation and manipulation of text is challenging and has limited success compared to recent deep generative modeling in visual domain. This paper aims at generating plausible natural language sentences, whose attributes are dynamically controlled by learning disentangled latent representations with designated…
We consider the clustering problem of attributed graphs. Our challenge is how we can design an effective and efficient clustering method that precisely captures the hidden relationship between the topology and the attributes in real-world graphs. We propose Non-linear Attributed Graph Clustering by Symmetric Non-negati…
A method for trust evaluation of devices in human-device coexistence systems.
Study examines how machine learning attribution methods reflect risk in finance.
Proposes a new method for fairness in machine learning with multiple protected attributes.
This extended abstract presents a visualization system, which is designed for domain scientists to visually understand their deep learning model of extracting multiple attributes in x-ray scattering images. The system focuses on studying the model behaviors related to multiple structural attributes. It allows users to …
Current approaches for explaining machine learning models fall into two distinct classes: antecedent event influence and value attribution. The former leverages training instances to describe how much influence a training point exerts on a test point, while the latter attempts to attribute value to the features most pe…
Graph neural networks (GNNs) have shown great power in learning on attributed graphs. However, it is still a challenge for GNNs to utilize information faraway from the source node. Moreover, general GNNs require graph attributes as input, so they cannot be appled to plain graphs. In the paper, we propose new models nam…
Graph Prototypical Networks improve few-shot node classification on attributed networks.
In-Run Data Shapley offers efficient data attribution for large-scale models.
Wavelet Attribution Method (WAM) improves feature attribution for deep models.
New method combines hypergraph structure and node attributes for better community detection.
CDLEEDS detects local changes in evolving data streams for accurate feature attributions.
Feature attribution methods, which explain an individual prediction made by a model as a sum of attributions for each input feature, are an essential tool for understanding the behavior of complex deep learning models. However, ensuring that models produce meaningful explanations, rather than ones that rely on noise, i…