Search Results for author:
Found 8 papers, 2 papers with code
Gradient-Aware Logit Adjustment Loss for Long-tailed Classifier
Additionally, We find that most of the solutions to long-tailed problems are still biased towards head classes in the end, and we propose a simple and post hoc prediction re-balancing strategy to further mitigate the basis toward head class.
Analyzing and Reducing Catastrophic Forgetting in Parameter Efficient Tuning
Through extensive experiments, we uncover the mode connectivity phenomenon in the LLMs continual learning scenario and find that it can strike a balance between plasticity and stability.
EsaCL: Efficient Continual Learning of Sparse Models
A key challenge in the continual learning setting is to efficiently learn a sequence of tasks without forgetting how to perform previously learned tasks.
T-SaS: Toward Shift-aware Dynamic Adaptation for Streaming Data
Discovering the shifted behaviors and the evolving patterns underlying the streaming data are important to understand the dynamic system.
Graph Relation Aware Continual Learning
Learning a single model could loss discriminative information for each graph task while the model expansion scheme suffers from high model complexity.
Read, Diagnose and Chat: Towards Explainable and Interactive LLMs-Augmented Depression Detection in Social Media
This paper proposes a new depression detection system based on LLMs that is both interpretable and interactive.
Mitigating Popularity Bias in Recommendation with Unbalanced Interactions: A Gradient Perspective
We present a gradient perspective to understand two negative impacts of popularity bias in recommendation model optimization: (i) the gradient direction of popular item embeddings is closer to that of positive interactions, and (ii) the magnitude of positive gradient for popular items are much greater than that of unpopular items.
Semi-supervised Drifted Stream Learning with Short Lookback
In many scenarios, 1) data streams are generated in real time; 2) labeled data are expensive and only limited labels are available in the beginning; 3) real-world data is not always i. i. d.
