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.
LaMP neural networks model label interactions for multi-label classification.
Simplified interactive image segmentation using kNN graphs.
DPBD simplifies labeling functions through interactive demonstrations.
Visual reranking is effective to improve the performance of the text-based video search. However, existing reranking algorithms can only achieve limited improvement because of the well-known semantic gap between low level visual features and high level semantic concepts. In this paper, we adopt interactive video search…
FLDCRF improves sequence labeling performance with latent dynamics interactions.
We study the problem of interactively learning a binary classifier using noisy labeling and pairwise comparison oracles, where the comparison oracle answers which one in the given two instances is more likely to be positive. Learning from such oracles has multiple applications where obtaining direct labels is harder bu…
Graph neural network predicts vehicle interactions and trajectories for autonomous driving.
Enhances LDL by integrating distance and directional information for more robust label feature representation.
Interactive learning is a process in which a machine learning algorithm is provided with meaningful, well-chosen examples as opposed to randomly chosen examples typical in standard supervised learning. In this paper, we propose a new method for interactive learning from multiple noisy labels where we exploit the disagr…
Interactive weak supervision learns useful heuristics from user feedback.
Study quantifies interactions between unlabeled multimodal data.
Interactive machine learning improves learning efficiency with user input.
Nemo improves WS learning pipeline by 20%.
Protein-protein interaction (PPI) prediction is an important problem in machine learning and computational biology. However, there is no data set for training or evaluation purposes, where all the instances are accurately labeled. Instead, what is available are instances of positive class (with possibly noisy labels) a…
A new model embeds word and label hierarchies in hyperbolic space for HMLC.
Develops methods for clustering hypergraphs with categorical edge labels.
Study efficient interactive learning for structured outputs with reliable computation.
XLabel tool reduces medical experts' workload by 40% and explains its decisions.
HopGAT improves node classification in sparsely labeled graphs by learning from distant neighbors.
We introduce structured prediction energy networks (SPENs), a flexible framework for structured prediction. A deep architecture is used to define an energy function of candidate labels, and then predictions are produced by using back-propagation to iteratively optimize the energy with respect to the labels. This deep a…
Improved drug-protein interaction prediction using FTL method.
In this work, we introduce a novel framework that employs cluster annotation to boost active learning by reducing the number of human interactions required to train deep neural networks. Instead of annotating single samples individually, humans can also label clusters, producing a higher number of annotated samples wit…
In this work we present the novel ASTRID method for investigating which attribute interactions classifiers exploit when making predictions. Attribute interactions in classification tasks mean that two or more attributes together provide stronger evidence for a particular class label. Knowledge of such interactions make…
GENN predicts drug interactions by modeling correlations between link labels.
We tackle the problem of inferring node labels in a partially labeled graph where each node in the graph has multiple label types and each label type has a large number of possible labels. Our primary example, and the focus of this paper, is the joint inference of label types such as hometown, current city, and employe…
An interactive image retrieval system learns which images in the database belong to a user's query concept, by analyzing the example images and feedback provided by the user. The challenge is to retrieve the relevant images with minimal user interaction. In this work, we propose to solve this problem by posing it as a …
Drug-drug interactions (DDIs) are a major cause of preventable hospitalizations and deaths. Predicting the occurrence of DDIs helps drug safety professionals allocate investigative resources and take appropriate regulatory action promptly. Traditional DDI prediction methods predict DDIs based on the similarity between …
Study learning and refutation in non-interactive LDP, showing sample complexity equivalence.
One of the fundamental tasks in understanding genomics is the problem of predicting Transcription Factor Binding Sites (TFBSs). With more than hundreds of Transcription Factors (TFs) as labels, genomic-sequence based TFBS prediction is a challenging multi-label classification task. There are two major biological mechan…
We present an approach for building an active agent that learns to segment its visual observations into individual objects by interacting with its environment in a completely self-supervised manner. The agent uses its current segmentation model to infer pixels that constitute objects and refines the segmentation model …
Archipelago provides interpretable explanations of feature interactions in machine learning models.
We address the problem of semi-supervised learning in relational networks, networks in which nodes are entities and links are the relationships or interactions between them. Typically this problem is confounded with the problem of graph-based semi-supervised learning (GSSL), because both problems represent the data as …
Interactive machine learning with weak supervision and pre-trained embeddings.
An active learner is given a hypothesis class, a large set of unlabeled examples and the ability to interactively query labels to an oracle of a subset of these examples; the goal of the learner is to learn a hypothesis in the class that fits the data well by making as few label queries as possible. This work addresses…
CASTER predicts drug interactions using chemical substructures.
Collective classification models attempt to improve classification performance by taking into account the class labels of related instances. However, they tend not to learn patterns of interactions between classes and/or make the assumption that instances of the same class link to each other (assortativity assumption).…
New robust algorithms improve learning with feature feedback.
Interactive learning with hindsight instruction feedback achieves better performance than traditional methods.
Semi-automatic data annotation helps experts label unlabeled samples based on feature space projection.
Enhances image classification by integrating semantic hierarchy into CNN models.
Proposes ML-GCN for multi-label network node representation learning.
We study agnostic active learning, where the goal is to learn a classifier in a pre-specified hypothesis class interactively with as few label queries as possible, while making no assumptions on the true function generating the labels. The main algorithms for this problem are {\em{disagreement-based active learning}}, …
User interfaces provide an interactive window between physical and virtual environments. A new concept in the field of human-computer interaction is a soft user interface; a compliant surface that facilitates touch interaction through deformation. Despite the potential of these interfaces, they currently lack a signal …
Label assignment problems with large state spaces are important tasks especially in computer vision. Often the pairwise interaction (or smoothness prior) between labels assigned at adjacent nodes (or pixels) can be described as a function of the label difference. Exact inference in such labeling tasks is still difficul…
New method learns interpretable concepts from user feedback for high-dimensional data.
Predicts student performance in interactive online question pools using GNNs.
Unified analysis of multilabel Fisher discriminants with improved dimensionality and robustness.
Fair active learning selects data points to balance model accuracy and fairness.