Enhanced word embeddings boost multiclass text classification accuracy.
problem Improving multiclass text classification accuracy using pre-trained embeddings.
method Proposed word-class embeddings (WCEs) to enhance pre-trained word embeddings.
result WCEs significantly improve multiclass text classification accuracy.
Cost-effective method improves and re-purposes pre-trained GANs by fine-tuning class-embeddings.
problem Fine-tuning BigGANs from scratch is impractical due to instability and high computational cost.
method Fine-tuning only the class-embedding layer of pre-trained GANs.
result Significantly improved realism and diversity of samples, re-purposed for new tasks, and de-biased or improved diversity.
ECGs improve GNNs for non-homophilic data.
problem Improving GNNs for datasets where nodes are not likely to belong to the same class.
method ECGs rewire GNNs' computation graph to connect nodes likely in the same class using weaker classifiers.
result ECGs improve GNN performance on non-homophilic datasets.
Gen1S learns novel classes with 1-shot data using residual space and generative models.
problem Learning new classes with limited data in a growing dataset.
method Mapping embeddings to a residual space, using generative models to learn multi-modal distribution, and applying it as a structural prior.
result Consistent improvement over state-of-the-art methods in recognizing novel classes.
HGNN learns augmented features for deep multi-task learning.
problem Feature learning for deep multi-task learning.
method Hierarchical Graph Neural Network (HGNN) with two levels of graph neural networks.
result Significant performance improvement in classification tasks.
We propose a method for learning embeddings for few-shot learning that is suitable for use with any number of ways and any number of shots (shot-free). Rather than fixing the class prototypes to be the Euclidean average of sample embeddings, we allow them to live in a higher-dimensional space (embedded class models) an…
ELM improves neural model embeddings for long-tail learning.
problem Learning skewed label distributions in neural models.
method Enforces margins in logit space and regularizes embedding distribution.
result ELM reduces generalization gap and tightens tail class embeddings.
A new method for federated learning with only positive labels.
problem Learning with only positive labels leads to poor classifier performance.
method Federated Averaging with Spreadout (FedAwS) framework.
result FedAwS can almost match the performance of conventional learning with negative labels.
POET enables large neural network training on tiny devices with reduced energy.
problem Training large neural networks on memory-limited edge devices.
method Jointly optimizes rematerialization and paging for memory reduction, formulating an MILP for energy-efficient training.
result POET trains ResNet-18 and BERT within Cortex-M memory constraints, outperforming current methods in energy efficiency.
Study of pseudoconvex 3-manifolds in complex surfaces.
problem Understanding pseudoconvex 3-manifolds in complex surfaces.
method Develop tools for constructing topologically pseudoconvex embeddings and classify almost-complex structures.
result Every closed, oriented 3-manifold can be embedded in a compact complex surface realizing any homotopy class of almost-complex structures.
Federated learning framework improves model generalization and privacy.
problem Communication overhead and statistical heterogeneity in FL.
method Prototypes and lightweight adapters for local model refinement.
result Improves classification accuracy over baseline algorithms.
Study shows neural collapse is invariant to class imbalances under certain conditions.
problem Neural collapse properties are only valid for balanced data.
method Adopted UFM and introduced SELI for invariant characterization.
result Embeddings and classifiers always interpolate a simplex-encoded label matrix regardless of class imbalances.
Adapts pretrained models to new classes without additional training.
problem Training models on limited labels and predicting new, unseen classes.
method Uses Fréchet mean instead of argmax for prediction, leveraging metric space distances.
result Improves model performance on unseen classes by up to 29.7% on ImageNet.