We study the problem of optimizing biological sequences, e.g., proteins,...
Graph-based models have become increasingly important in various domains...
Recently, deep reinforcement learning (DRL) has shown promise in solving...
Generating graphs from a target distribution is a significant challenge
...
Recently, graph-based planning algorithms have gained much attention to ...
Concept bottleneck models (CBMs) are a class of interpretable neural net...
This paper studies graph-structured prediction for supervised learning o...
Designing a neural network architecture for molecular representation is
...
Neural networks are prone to be biased towards spurious correlations bet...
We consider the problem of searching an input maximizing a black-box
obj...
Abstract reasoning, i.e., inferring complicated patterns from given
obse...
Retrosynthetic planning is a fundamental problem in chemistry for findin...
Retrosynthesis, of which the goal is to find a set of reactants for
synt...
Recent discoveries on neural network pruning reveal that, with a careful...
Neural networks often learn to make predictions that overly rely on spur...
De novo molecular design attempts to search over the chemical space for
...
We propose a novel value-based algorithm for cooperative multi-agent
rei...
Designing efficient algorithms for combinatorial optimization appears
ub...
Transferring knowledge from a teacher neural network pretrained on the s...
Probabilistic graphical models are a key tool in machine learning
applic...
Computing the partition function Z of a discrete graphical model is a
fu...
Computing partition function is the most important statistical inference...
Markov Chain Monte Carlo (MCMC) and Belief Propagation (BP) are the most...
Max-product Belief Propagation (BP) is a popular message-passing algorit...