Search

We introduce rLLM (relationLLM), a PyTorch library designed for Relational Table Learning (RTL) with Large Language Models (LLMs). The core idea is to decompose state-of-the-art Graph Neural Networks, LLMs, and Table Neural Networks into standardized modules, to enable the fast construction of novel RTL-type models in a simple "combine, align, and co-train" manner. To illustrate the usage of rLLM, we introduce a simple RTL method named \textbf{BRIDGE}. Additionally, we present three novel relational tabular datasets (TML1M, TLF2K, and TACM12K) by enhancing classic datasets. We hope rLLM can serve as a useful and easy-to-use development framework for RTL-related tasks. Our code is available at: https://github.com/rllm-project/rllm.

This paper tackles the challenge of teaching code semantics to Large Language Models (LLMs) for program analysis by incorporating code symmetries into the model architecture. We introduce a group-theoretic framework that defines code symmetries as semantics-preserving transformations, where forming a code symmetry group enables precise and efficient reasoning of code semantics. Our solution, SymC, develops a novel variant of self-attention that is provably equivariant to code symmetries from the permutation group defined over the program dependence graph. SymC obtains superior performance on five program analysis tasks, outperforming state-of-the-art code models without any pre-training. Our results suggest that code LLMs that encode the code structural prior via the code symmetry group generalize better and faster.

Text-based games are a popular testbed for language-based reinforcement learning (RL). In previous work, deep Q-learning is commonly used as the learning agent. Q-learning algorithms are challenging to apply to complex real-world domains due to, for example, their instability in training. Therefore, in this paper, we adapt the soft-actor-critic (SAC) algorithm to the text-based environment. To deal with sparse extrinsic rewards from the environment, we combine it with a potential-based reward shaping technique to provide more informative (dense) reward signals to the RL agent. We apply our method to play difficult text-based games. The SAC method achieves higher scores than the Q-learning methods on many games with only half the number of training steps. This shows that it is well-suited for text-based games. Moreover, we show that the reward shaping technique helps the agent to learn the policy faster and achieve higher scores. In particular, we consider a dynamically learned value function as a potential function for shaping the learner's original sparse reward signals.

Robust topology optimization (RTO) improves the robustness of designs with respect to random sources in real-world structures, yet an accurate sensitivity analysis requires the solution of many systems of equations at each optimization step, leading to a high computational cost. To open up the full potential of RTO under a variety of random sources, this paper presents a momentum-based accelerated mirror descent stochastic approximation (AC-MDSA) approach to efficiently solve RTO problems involving various types of load uncertainties. The proposed framework can perform high-quality design updates with highly noisy stochastic gradients. We reduce the sample size to two (minimum for unbiased variance estimation) and show only two samples are sufficient for evaluating stochastic gradients to obtain robust designs, thus drastically reducing the computational cost. We derive the AC-MDSA update formula based on $\ell_1$-norm with entropy function, which is tailored to the geometry of the feasible domain. To accelerate and stabilize the algorithm, we integrate a momentum-based acceleration scheme, which also alleviates the step size sensitivity. Several 2D and 3D examples with various sizes are presented to demonstrate the effectiveness and efficiency of the proposed AC-MDSA framework to handle RTO involving various types of loading uncertainties., Comment: 38 pages (including reference)

Variance reduction (VR) techniques for convergence rate acceleration of stochastic gradient descent (SGD) algorithm have been developed with great efforts recently. VR's two variants, stochastic variance-reduced-gradient (SVRG-SGD) and importance sampling (IS-SGD) have achieved remarkable progresses. Meanwhile, asynchronous SGD (ASGD) is becoming more critical due to the ever-increasing scale of the optimization problems. The application of VR in ASGD to accelerate its convergence rate has therefore attracted much interest and SVRG-ASGDs are therefore proposed. However, we found that SVRG suffers dissatisfying performance in accelerating ASGD when the datasets are sparse and large-scale. In such case, SVRG-ASGD's iterative computation cost is magnitudes higher than ASGD which makes it very slow. On the other hand, IS achieves improved convergence rate with few extra computation cost and is invariant to the sparsity of dataset. This advantage makes it very suitable for the acceleration of ASGD for large-scale sparse datasets. In this paper we propose a novel IS-combined ASGD for effective convergence rate acceleration, namely, IS-ASGD. We theoretically prove the superior convergence bound of IS-ASGD. Experimental results also demonstrate our statements.