arXiv research

HGKT transfers knowledge from seen to unseen classes in GZSL without prior unseen class info.

RL agents fail to generalize to unseen environments, even when dynamics are similar.

CM algorithm improves MMI classifications for unseen instances.

After building a classifier with modern tools of machine learning we typically have a black box at hand that is able to predict well for unseen data. Thus, we get an answer to the question what is the most likely label of a given unseen data point. However, most methods will provide no answer why the model predicted th…

PReNet detects seen and unseen anomalies using pairwise relations.

In this paper we consider a version of the zero-shot learning problem where seen class source and target domain data are provided. The goal during test-time is to accurately predict the class label of an unseen target domain instance based on revealed source domain side information (\eg attributes) for unseen classes. …

TGG improves zero-shot and few-shot learning by explicitly modeling and utilizing seen-unseen domain relations.

Neural network models that are not conditioned on class identities were shown to facilitate knowledge transfer between classes and to be well-suited for one-shot learning tasks. Following this motivation, we further explore and establish such models and present a novel neural network architecture for the task of weakly…

A new framework improves few-shot classification by learning to generalize to unseen classes.

Proposes a new method for MIR using kernel mean embeddings.

Proposes a few-shot learning method for feature selection without labeled data.

The paper extends multiple instance learning to multiclass and regression problems.

Algorithms for equilibrium computation generally make no attempt to ensure that the computed strategies are understandable by humans. For instance the strategies for the strongest poker agents are represented as massive binary files. In many situations, we would like to compute strategies that can actually be implement…

New method learns domain-invariant features for unseen domains.

Adaptive adjustment of semantic feature space improves zero-shot recognition.

This paper studies the problem of Generalized Zero-shot Learning (G-ZSL), whose goal is to classify instances belonging to both seen and unseen classes at the test time. We propose a novel space decomposition method to solve G-ZSL. Some previous models with space decomposition operations only calibrate the confident pr…

OwMatch improves open-world semi-supervised learning by self-labeling and consistency.

The paper explores how different network architectures learn logical functions under GOTU, finding that a min-degree-interpolator is learned.

A new method for MIR in remote sensing without assuming a prime instance per bag.

This paper improves multi-label classification by leveraging high-order label correlations.

Training 3D object detectors for autonomous driving has been limited to small datasets due to the effort required to generate annotations. Reducing both task complexity and the amount of task switching done by annotators is key to reducing the effort and time required to generate 3D bounding box annotations. This paper…

RaRecognize learns to recognize rare classes in a stream of data.

Efficiently solves heterogeneous QPs by reducing variables using instance-specific projections.

Unified approach to continual learning using generative replay and open set recognition.

Perhaps surprisingly, it is possible to predict how long an algorithm will take to run on a previously unseen input, using machine learning techniques to build a model of the algorithm's runtime as a function of problem-specific instance features. Such models have important applications to algorithm analysis, portfolio…

Differentiable cutting-plane layers solve parametric mixed-integer linear optimization problems.

Deep RL learns effective job shop scheduling rules from raw features.

Meta-learning improves anomaly detection with few labeled instances.

Meta-dropout learns to perturb training examples for better generalization.

Conventional Neural Architecture Search (NAS) aims at finding a single architecture that achieves the best performance, which usually optimizes task related learning objectives such as accuracy. However, a single architecture may not be representative enough for the whole dataset with high diversity and variety. Intuit…

Modified Meta-TS for linear contextual bandits reduces regret.

A group of transition probability functions form a Shannon's channel whereas a group of truth functions form a semantic channel. Label learning is to let semantic channels match Shannon's channels and label selection is to let Shannon's channels match semantic channels. The Channel Matching (CM) algorithm is provided f…

New method finds unseen states for RL, improving performance.

Bayesian TAML balances meta-knowledge and task-specific learning for imbalanced tasks.

New method learns better branching policies for MILP problems.

RL optimizes quantum circuit parameters for combinatorial problems.

Paper proposes machine learning to optimize QAOA for combinatorial problems.

We present CROSSGRAD, a method to use multi-domain training data to learn a classifier that generalizes to new domains. CROSSGRAD does not need an adaptation phase via labeled or unlabeled data, or domain features in the new domain. Most existing domain adaptation methods attempt to erase domain signals using technique…

DUET optimizes LLM training data mixtures using feedback from unseen tasks.

MKD learns MTS attributes to reconstruct and cluster unseen classes.

A deep generative model learns from seen and unseen classes without explicit training data.

Meta-agent learns effective exploration from offline data.

Sensory data are often comprised of independent content and transformation factors. For example, face images may have shapes as content and poses as transformation. To infer separately these factors from given data, various ``disentangling'' models have been proposed. However, many of these are supervised or semi-super…

The study evaluates neural network patching techniques to adapt models to concept drift.

New method calibrates neural network predictions for better reliability.

A new network learns to prioritize messages for efficient multi-robot path planning.

Multiple Additive Regression Trees (MART), an ensemble model of boosted regression trees, is known to deliver high prediction accuracy for diverse tasks, and it is widely used in practice. However, it suffers an issue which we call over-specialization, wherein trees added at later iterations tend to impact the predicti…

Proposes OpenKI for better web-scale knowledge extraction and alignment.