ZSL-KG learns class representations from common sense knowledge graphs.
problem Predicting classes without labeled examples using semantic class representations.
method TrGCN, a novel transformer graph convolutional network, embeds nodes from common sense knowledge graphs in a vector space.
result ZSL-KG improves over existing methods on five out of six zero-shot benchmark datasets.
ZK-GanDef uses GANs to defend against adversarial examples without using them during training.
problem Adversarial examples challenge the effectiveness of neural network classifiers.
method Generative adversarial net (GAN) based zero knowledge adversarial training defense.
result Enhances test accuracy on adversarial examples by up to 49.17% compared to zero knowledge approaches.
Paper tackles zero-shot learning for semantic image interpretation.
problem Extracting structured semantic descriptions from images requires complete training sets, which are often unavailable.
method Uses Logic Tensor Networks to leverage logical constraints and similarities among relationships in the training set.
result Background knowledge can alleviate the incompleteness of training sets, improving zero-shot learning performance.
Zero-shot KD for object detection without training data.
problem Challenges in using training data for knowledge distillation.
method Synthesizes pseudo-targets and samples using pretrained network.
result Achieves respectable mAP on object detection benchmarks.
Zero-shot learning transfers knowledge from seen classes to novel unseen classes to reduce human labor of labelling data for building new classifiers. Much effort on zero-shot learning however has focused on the standard multi-class setting, the more challenging multi-label zero-shot problem has received limited attent…
FedZKT enables resource-constrained devices to participate in federated learning with heterogeneous models.
problem Inequality in resource allocation hinders participation from resource-constrained devices in federated learning.
method Zero-shot knowledge transfer through a server-assigned distillation process.
result FedZKT effectively transfers knowledge across heterogeneous on-device models without requiring comparable local training efforts.
HGKT transfers knowledge from seen to unseen classes in GZSL without prior unseen class info.
problem Learning to classify unseen classes in GZSL.
method Structured heterogeneous graph with graph neural network for knowledge transfer.
result Achieves state-of-the-art results on public benchmark datasets.
PHAZE framework uses zkML and hashing for fast, verifiable LHC trigger decisions.
problem Inefficient inference on large machine learning models for LHC trigger performance.
method Cryptographic techniques like hashing and zkML for low latency, certifiable inference.
result Achieves nanosecond-order latency for LHC triggers, enabling dynamic low-level triggers.
This paper presents the development of a hybrid learning system based on Support Vector Machines (SVM), Adaptive Neuro-Fuzzy Inference System (ANFIS) and domain knowledge to solve prediction problem. The proposed two-stage Domain Knowledge based Fuzzy Information System (DKFIS) improves the prediction accuracy attained…
Adaptive adjustment of semantic feature space improves zero-shot recognition.
problem Domain shift and hubness problems in zero-shot recognition.
method Adaptive adjustment of semantic feature space.
result Remarkable performance improvement compared to existing methods.
Two KG-based methods explain transfer learning in CNN and ZSL.
problem Uninterpretable transfer learning for non-ML experts.
method Knowledge Graph-based explanation for transferability and model justification.
result Rich, human-understandable explanations for transfer learning.
A new method transfers knowledge without data, matching teacher's predictions closely.
problem Lack of access to training data for knowledge transfer.
method Adversarial training to match teacher's predictions without data.
result Zero-shot student performs well on CIFAR10, improving state-of-the-art.
Paper derives formulas for volatility swap strike and zero vanna implied volatility.
problem Relationship between volatility swap strike and zero vanna implied volatility.
method Applied Malliavin calculus to derive exact formulas.
result Zero vanna implied volatility is a better approximation for volatility swap strike.
OTSeg uses multi-prompt Sinkhorn attention to improve zero-shot semantic segmentation.
problem Leveraging pre-trained CLIP knowledge to align text embeddings with pixel embeddings.
method OTSeg employs Multi-Prompts Sinkhorn (MPS) and Multi-Prompts Sinkhorn Attention (MPSA) to enhance semantic feature matching.
result OTSeg achieves state-of-the-art performance in zero-shot semantic segmentation tasks.
Paper proposes a new process for GZSL improving recognition performance on unseen classes.
problem Maximizing recognition performance on unseen classes in ZSL.
method Proposes a new training and evaluation process that penalizes samples from seen classes to improve performance on unseen classes.
result Significant performance boost on CUB and AwA2 datasets.
Student-teacher learning improves generalization with noisy inputs.
problem Transfer knowledge from clean inputs to noisy inputs.
method Analyzes student-teacher learning using deep linear networks and experiments with nonlinear networks.
result Three factors are vital for success: zero training loss, teacher knowledge, and feature decomposition.
A new method trains a smaller model from a larger one without needing the actual training data.
problem Training a smaller model from a larger one without access to the training data.
method Synthesizes data impressions from the Teacher model to train the Student model.
result Zero-Shot Knowledge Distillation achieves competitive generalization performance.
New algorithm finds near-optimal policies efficiently in zero-sum games.
problem Lack of provable efficiency guarantees for policy optimization in zero-sum games.
method Policy optimization algorithm with function approximation.
result Proves efficient convergence to near-optimal policies with polynomial samples and iterations.
Semantic embeddings improve safety-critical classifier performance.
problem Improving interpretability and error detection in safety-critical neural networks.
method Created embeddings from symbolic domain knowledge, used for misprediction interpretation and error detection, introduced semantic distance for confidence measurement.
result Semantic distance achieves near state-of-the-art performance in a traffic sign classifier, faster than other methods.
This paper enhances language models with knowledge awareness.
problem Understanding how much knowledge pretrained language models grasp.
method Inserting explicit knowledge layers into pretraining without changing transformer architecture.
result Significantly more knowledge packed into transformer parameters.
ZegOT uses optimal transport to zero-shot segment images with text prompts.
problem Zero-shot semantic segmentation with limited image-text alignment knowledge.
method ZegOT uses optimal transport to match multiple text prompts with frozen image embeddings.
result ZegOT achieves state-of-the-art performance in zero-shot semantic segmentation.
KG-WDRO optimizes transfer learning with external knowledge.
problem Over-pessimism in WDRO for small target samples.
method KG-WDRO incorporates multiple sources of external knowledge to construct smaller Wasserstein ambiguity sets.
result KG-WDRO improves transfer learning performance and adaptivity.
Graph networks learn symbolic physics laws from simulations.
problem Learning interpretable physics laws from simulations.
method Inductive biases on graph networks for symbolic regression.
result Graph networks can learn symbolic laws of physics.
Knowledge transfer between tasks can improve the performance of learned models, but requires an accurate estimate of the inter-task relationships to identify the relevant knowledge to transfer. These inter-task relationships are typically estimated based on training data for each task, which is inefficient in lifelong …
Improved zero-shot learning with graph-based regularization.
problem Transfer knowledge to unknown classes in zero-shot learning.
method Isoperimetric loss for learning map between visual and semantic embeddings, exploiting graph structure.
result Regularization alone outperforms state-of-the-art methods in zero-shot learning benchmarks.
Study evaluates ZSL methods for unseen hashtag predictions from tweet text.
problem Lack of labeled data for all possible hashtag labels in supervised training.
method Proposed a Zero Shot Learning (ZSL) paradigm to predict unseen hashtag labels.
result Demonstrated effectiveness and scalability of ZSL methods for unseen hashtag recommendations.
A novel regression algorithm uses shape analysis to predict curves without training data.
problem Predicting curves without training data for regression problems.
method Shape analysis of trained models to generate new shapes for prediction.
result Successfully predicts curves based on shape analysis of existing models.
Despite the advancement of supervised image recognition algorithms, their dependence on the availability of labeled data and the rapid expansion of image categories raise the significant challenge of zero-shot learning. Zero-shot learning (ZSL) aims to transfer knowledge from labeled classes into unlabeled classes to r…
Context-aware ZSL improves object recognition by considering object context.
problem Previous ZSL approaches ignore object context, limiting their effectiveness.
method Proposes a new approach that models the conditional likelihood of objects appearing in specific contexts.
result Contextual information significantly improves ZSL performance and is robust to class imbalance.
Policy optimization converges to Nash equilibria in zero-sum LQ games.
problem Finding Nash equilibria in zero-sum linear quadratic games.
method Developed three projected nested-gradient methods to converge to NE.
result Policy optimization methods converge to Nash equilibria in zero-sum LQ games.
The high-dimensional linear model y=Xβ0+ε is considered and the focus is put on the problem of recovering the support S0 of the sparse vector β0. We introduce Lasso-Zero, a new ℓ1-based estimator whose novelty resides in an "overfit, then threshold" paradigm and the use of noise dictionaries concate…
Proposes AMS-SFE to improve zero-shot learning by aligning semantic feature spaces.
problem Domain shift problem in zero-shot learning due to disjoint seen and unseen data.
method Expands semantic features using an autoencoder and aligns them with visual feature manifold.
result Remarkable performance improvement over existing methods.
Confidential Guardian prevents model abstention from being used to discriminate.
problem Dishonest institutions can exploit machine learning model abstention to unfairly deny services.
method Confidential Guardian uses zero-knowledge proofs to verify model confidence and detect suppression.
result Confidential Guardian effectively prevents the misuse of cautious predictions.
Study examines flaws in probing LLMs' knowledge and introduces a new method.
problem Flaws in existing methods for probing the veracity of LLMs' internal knowledge.
method sAwMIL (Sparse-Aware Multiple-Instance Learning) combining multiple-instance learning with conformal prediction.
result LLMs encode a third type of signal distinct from true and false.
Bad models can teach well by replicating noise.
problem Overparameterized models can replicate noise in training data.
method Knowledge distillation from noisy samplers.
result Distillation from samplers approximates Bayes optimal classifier.
New approach allows deep learning to adapt to new tasks without explicit training.
problem How to reuse deep learning knowledge for new tasks without explicit training.
method Homoiconic Meta-Mapping (HoMM) that transforms task representations.
result Zero-shot remapping of behavior to adapt to new tasks.
We study high-dimensional asymptotic performance limits of binary supervised classification problems where the class conditional densities are Gaussian with unknown means and covariances and the number of signal dimensions scales faster than the number of labeled training samples. We show that the Bayes error, namely t…
EQD model improves domain-specific QA by 0.6% to 10.5%.
problem Challenges in domain-specific quantitative reasoning for LLMs.
method Two-step fine-tuning framework guided by a reward function.
result EQD outperforms state-of-the-art models and prompting strategies.
GANs improve VSR accuracy by generating unseen classes.
problem Scarcity of training data for unseen classes in VSR.
method Generative Adversarial Networks (GANs) to generate new class samples.
result Accuracy increased by 27% for unseen classes.
New algorithm solves complex optimization problems efficiently.
problem Minimizing convex upper-level functions over optimal lower-level solutions.
method Reformulates bilevel problems into functionally constrained problems, achieving near-optimal rates.
result Achieves near-optimal rates for both smooth and nonsmooth problems.
Study of 2imes2 zero-sum games with noisy observations and commitments.
problem Analyzing 2imes2 zero-sum games with noisy observations and commitments. method Modeling a 2imes2 zero-sum game with a leader committing to a strategy and a follower observing a noisy version of the leader's action. result Observing the leader's action is either beneficial or immaterial for the follower, and the equilibrium payoff is bounded.
Study learns optimal strategies in imperfect information games with self-play.
problem Learning optimal strategies in imperfect information games.
method Proposes Follow the Regularized Leader (FTRL) algorithms for imperfect information games.
result Proposes two FTRL algorithms: Balanced FTRL and Adaptive FTRL.
Theory of point vortices extended to closed surfaces.
problem Extending point vortex dynamics to closed surfaces.
method Unified theory of point vortex dynamics on the plane, sphere, and closed surfaces.
result Comprehensive guide to point vortex dynamics on closed surfaces with genus zero and vanishing total vorticity.
Proposes an autonomous IDS using multiple learning techniques.
problem Autonomous and zero-day attack detection in IDS.
method Parallel use of GRU, CNN, and random forest; majority vote and OR logic combination.
result Achieved high accuracy (87.28%) on NSL-KDD's 'KDDTest+' dataset.
MoleculeSTM learns from molecule structures and texts for better drug design.
problem Lack of integration between chemical structures and textual knowledge in AI drug discovery.
method Jointly learns chemical structures and texts via contrastive learning, using a large dataset.
result MoleculeSTM achieves state-of-the-art performance in zero-shot tasks like structure-text retrieval and molecule editing.
New model allows some connections to be zero, improving network analysis.
problem Networks with block structure and sparsity.
method Sparse Popularity Adjusted Stochastic Block Model (PABM).
result Allows some probabilities of connections to be zero.
Modular neural causal models outperform other models in generalization and adaptation.
problem Robust out-of-distribution generalization and fast adaptation in machine learning.
method Factorizing data generating process into modules using only causal parents as predictors.
result Modular neural causal models offer robust generalization and fast adaptation, especially in low data regimes.
We look at complete minimal surfaces of finite total curvature in R4. Similarly to the case of complex curves in C2 we introduce their {\it link at infinity}; we derive the {\it writhe number at infinity} which gives a formula for the total normal curvature of the surface. The knowledge of the l…