Search Results for author:
Found 12 papers, 2 papers with code
Preference Elicitation with Soft Attributes in Interactive Recommendation
Leveraging concept activation vectors for soft attribute semantics, we develop novel preference elicitation methods that can accommodate soft attributes and bring together both item and attribute-based preference elicitation.
How Bad is Top-$K$ Recommendation under Competing Content Creators?
Content creators compete for exposure on recommendation platforms, and such strategic behavior leads to a dynamic shift over the content distribution.
Learning from a Learning User for Optimal Recommendations
In real-world recommendation problems, especially those with a formidably large item space, users have to gradually learn to estimate the utility of any fresh recommendations from their experience about previously consumed items.
Uncoupled Bandit Learning towards Rationalizability: Benchmarks, Barriers, and Algorithms
Under the uncoupled learning setup, the last-iterate convergence guarantee towards Nash equilibrium is shown to be impossible in many games.
DeepSteal: Advanced Model Extractions Leveraging Efficient Weight Stealing in Memories
Secondly, we propose a novel substitute model training algorithm with Mean Clustering weight penalty, which leverages the partial leaked bit information effectively and generates a substitute prototype of the target victim model.
Learning the Optimal Recommendation from Explorative Users
We propose a new problem setting to study the sequential interactions between a recommender system and a user.
RA-BNN: Constructing Robust & Accurate Binary Neural Network to Simultaneously Defend Adversarial Bit-Flip Attack and Improve Accuracy
Apart from recovering the inference accuracy, our RA-BNN after growing also shows significantly higher resistance to BFA.
Reversible Action Design for Combinatorial Optimization with Reinforcement Learning
Combinatorial optimization problem (COP) over graphs is a fundamental challenge in optimization.
PAC-Learning for Strategic Classification
In this paper, we generalize both of these through a unified framework for strategic classification, and introduce the notion of strategic VC-dimension (SVC) to capture the PAC-learnability in our general strategic setup.
T-BFA: Targeted Bit-Flip Adversarial Weight Attack
Prior works of BFA focus on un-targeted attack that can hack all inputs into a random output class by flipping a very small number of weight bits stored in computer memory.
DeepHammer: Depleting the Intelligence of Deep Neural Networks through Targeted Chain of Bit Flips
Security of machine learning is increasingly becoming a major concern due to the ubiquitous deployment of deep learning in many security-sensitive domains.
Greedy Step Averaging: A parameter-free stochastic optimization method
In this paper we present the greedy step averaging(GSA) method, a parameter-free stochastic optimization algorithm for a variety of machine learning problems.
