Search Results for author:
Found 17 papers, 7 papers with code
TARDIS: Mitigate Temporal Misalignment via Representation Steering
Our experiments reveal that TARDIS enhances downstream task performance without the need for fine-tuning, can mitigate temporal misalignment even when exact target time period data is unavailable, and remains efficient even when the temporal information of the target data points is unknown at inference time.
Partial-Multivariate Model for Forecasting
When solving forecasting problems including multiple time-series features, existing approaches often fall into two extreme categories, depending on whether to utilize inter-feature information: univariate and complete-multivariate models.
Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMs
Large Language Models (LLMs) have demonstrated strong reasoning and memorization capabilities via pretraining on massive textual corpora.
Practical and Reproducible Symbolic Music Generation by Large Language Models with Structural Embeddings
Music generation introduces challenging complexities to large language models.
Learning Equi-angular Representations for Online Continual Learning
Online continual learning suffers from an underfitted solution due to insufficient training for prompt model update (e. g., single-epoch training).
Curve Your Attention: Mixed-Curvature Transformers for Graph Representation Learning
Real-world graphs naturally exhibit hierarchical or cyclical structures that are unfit for the typical Euclidean space.
3D Denoisers are Good 2D Teachers: Molecular Pretraining via Denoising and Cross-Modal Distillation
Pretraining molecular representations from large unlabeled data is essential for molecular property prediction due to the high cost of obtaining ground-truth labels.
Mixed-Curvature Transformers for Graph Representation Learning papersreview
Real-world graphs naturally exhibit hierarchical or cyclical structures that are unfit for the typical Euclidean space.
Learning to Unlearn: Instance-wise Unlearning for Pre-trained Classifiers
Since the recent advent of regulations for data protection (e. g., the General Data Protection Regulation), there has been increasing demand in deleting information learned from sensitive data in pre-trained models without retraining from scratch.
Transformers meet Stochastic Block Models: Attention with Data-Adaptive Sparsity and Cost
The forward and backward cost are thus linear to the number of edges, which each attention head can also choose flexibly based on the input.
Improving Multi-fidelity Optimization with a Recurring Learning Rate for Hyperparameter Tuning
However, it often results in selecting a sub-optimal configuration as training with the high-performing configuration typically converges slowly in an early phase.
Grouping-matrix based Graph Pooling with Adaptive Number of Clusters
Conventional methods ask users to specify an appropriate number of clusters as a hyperparameter, then assume that all input graphs share the same number of clusters.
Equivariant Hypergraph Neural Networks
Many problems in computer vision and machine learning can be cast as learning on hypergraphs that represent higher-order relations.
Pure Transformers are Powerful Graph Learners
We show that standard Transformers without graph-specific modifications can lead to promising results in graph learning both in theory and practice.
Ranked #5 on
Graph Regression
on PGR
Rebalancing Batch Normalization for Exemplar-based Class-Incremental Learning
The main reason for the ineffectiveness of their method lies in not fully addressing the data imbalance issue, especially in computing the gradients for learning the affine transformation parameters of BN.
On-the-Fly Rectification for Robust Large-Vocabulary Topic Inference
Across many data domains, co-occurrence statistics about the joint appearance of objects are powerfully informative.
Practical Correlated Topic Modeling and Analysis via the Rectified Anchor Word Algorithm
Despite great scalability on large data and their ability to understand correlations between topics, spectral topic models have not been widely used due to the absence of reliability in real data and lack of practical implementations.
