Ser-Nam Lim

Enhancing Adversarial Example Transferability With an Intermediate Level Attack

2019

Neural networks are vulnerable to adversarial examples, malicious inputs crafted to fool trained models. Adversarial examples often exhibit black-box transfer, meaning that adversarial examples for one model can fool another model. However, adversarial examples are …

Three New Validators and a Large-Scale Benchmark Ranking for Unsupervised Domain Adaptation

2022 · arXiv (Cornell University)

Changes to hyperparameters can have a dramatic effect on model accuracy. Thus, the tuning of hyperparameters plays an important role in optimizing machine-learning models. An integral part of the hyperparameter-tuning process is the evaluation of …

Computationally Budgeted Continual Learning: What Does Matter?

2023 · arXiv (Cornell University)

Continual Learning (CL) aims to sequentially train models on streams of incoming data that vary in distribution by preserving previous knowledge while adapting to new data. Current CL literature focuses on restricted access to previously …

Graph Inductive Biases in Transformers without Message Passing

2023 · arXiv (Cornell University)

Transformers for graph data are increasingly widely studied and successful in numerous learning tasks. Graph inductive biases are crucial for Graph Transformers, and previous works incorporate them using message-passing modules and/or positional encodings. However, Graph …

From Categories to Classifiers: Name-Only Continual Learning by Exploring the Web

2023 · arXiv (Cornell University)

Continual Learning (CL) often relies on the availability of extensive annotated datasets, an assumption that is unrealistically time-consuming and costly in practice. We explore a novel paradigm termed name-only continual learning where time and cost …