Toxic content detection is crucial for online services to remove inappropriate content that violates community standards. To automate the detection process, prior works have proposed varieties of machine learning (ML) approaches to train Language Models (LMs) for toxic content detection. However, both their accuracy and transferability across datasets are limited. Recently, Large Language Models (LLMs) have shown promise in toxic content detection due to their superior zero-shot and few-shot in-context learning ability as well as broad transferability on ML tasks. However, efficiently designing prompts for LLMs remains challenging. Moreover, the high run-time cost of LLMs may hinder their deployments in production. To address these challenges, in this work, we propose BD-LLM, a novel and efficient approach to Bootstrapping and Distilling LLMs for toxic content detection. Specifically, we design a novel prompting method named Decision-Tree-of-Thought (DToT) to bootstrap LLMs' detection performance and extract high-quality rationales. DToT can automatically select more fine-grained context to re-prompt LLMs when their responses lack confidence. Additionally, we use the rationales extracted via DToT to fine-tune student LMs. Our experimental results on various datasets demonstrate that DToT can improve the accuracy of LLMs by up to 4.6%. Furthermore, student LMs fine-tuned with rationales extracted via DToT outperform baselines on all datasets with up to 16.9\% accuracy improvement, while being more than 60x smaller than conventional LLMs. Finally, we observe that student LMs fine-tuned with rationales exhibit better cross-dataset transferability.
Federated Learning (FL) with Secure Aggregation (SA) has gained significant attention as a privacy preserving framework for training machine learning models while preventing the server from learning information about users' data from their individual encrypted model updates. Recent research has extended privacy guarantees of FL with SA by bounding the information leakage through the aggregate model over multiple training rounds thanks to leveraging the "noise" from other users' updates. However, the privacy metric used in that work (mutual information) measures the on-average privacy leakage, without providing any privacy guarantees for worse-case scenarios. To address this, in this work we study the conditions under which FL with SA can provide worst-case differential privacy guarantees. Specifically, we formally identify the necessary condition that SA can provide DP without addition noise. We then prove that when the randomness inside the aggregated model update is Gaussian with non-singular covariance matrix, SA can provide differential privacy guarantees with the level of privacy $ε$ bounded by the reciprocal of the minimum eigenvalue of the covariance matrix. However, we further demonstrate that in practice, these conditions are almost unlikely to hold and hence additional noise added in model updates is still required in order for SA in FL to achieve DP. Lastly, we discuss the potential solution of leveraging inherent randomness inside aggregated model update to reduce the amount of addition noise required for DP guarantee.
The classic studies of causal emergence have revealed that in some Markovian dynamical systems, far stronger causal connections can be found on the higher-level descriptions than the lower-level of the same systems if we coarse-grain the system states in an appropriate way. However, identifying this emergent causality from the data is still a hard problem that has not been solved because the correct coarse-graining strategy can not be found easily. This paper proposes a general machine learning framework called Neural Information Squeezer to automatically extract the effective coarse-graining strategy and the macro-state dynamics, as well as identify causal emergence directly from the time series data. By decomposing a coarse-graining operation into two processes: information conversion and information dropping out, we can not only exactly control the width of the information channel, but also can derive some important properties analytically including the exact expression of the effective information of a macro-dynamics. We also show how our framework can extract the dynamics on different levels and identify causal emergence from the data on several exampled systems.
Modeling the joint distribution of high-dimensional data is a central task in unsupervised machine learning. In recent years, many interests have been attracted to developing learning models based on tensor networks, which have the advantages of a principle understanding of the expressive power using entanglement properties, and as a bridge connecting classical computation and quantum computation. Despite the great potential, however, existing tensor network models for unsupervised machine learning only work as a proof of principle, as their performance is much worse than the standard models such as restricted Boltzmann machines and neural networks. In this Letter, we present autoregressive matrix product states (AMPS), a tensor network model combining matrix product states from quantum many-body physics and autoregressive modeling from machine learning. Our model enjoys the exact calculation of normalized probability and unbiased sampling. We demonstrate the performance of our model using two applications, generative modeling on synthetic and real-world data, and reinforcement learning in statistical physics. Using extensive numerical experiments, we show that the proposed model significantly outperforms the existing tensor network models and the restricted Boltzmann machines, and is competitive with state-of-the-art neural network models.
Jiang Zhang, Ivan Beschastnikh, Sergey Mechtaev et al.
Data-driven decision making is gaining prominence with the popularity of various machine learning models. Unfortunately, real-life data used in machine learning training may capture human biases, and as a result the learned models may lead to unfair decision making. In this paper, we provide a solution to this problem for decision trees and random forests. Our approach converts any decision tree or random forest into a fair one with respect to a specific data set, fairness criteria, and sensitive attributes. The \emph{FairRepair} tool, built based on our approach, is inspired by automated program repair techniques for traditional programs. It uses an SMT solver to decide which paths in the decision tree could have their outcomes flipped to improve the fairness of the model. Our experiments on the well-known adult dataset from UC Irvine demonstrate that FairRepair scales to realistic decision trees and random forests. Furthermore, FairRepair provides formal guarantees about soundness and completeness of finding a repair. Since our fairness-guided repair technique repairs decision trees and random forests obtained from a given (unfair) data-set, it can help to identify and rectify biases in decision-making in an organisation.
Link prediction aims to infer missing links or predicting the future ones based on currently observed partial networks, it is a fundamental problem in network science with tremendous real-world applications. However, conventional link prediction approaches neither have high prediction accuracy nor being capable of revealing the hidden information behind links. To address this problem, we generalize the latest techniques in deep learning on graphs and present a new link prediction model - DeepLinker. Instead of learning node representation with the node label information, DeepLinker uses the links as supervised information. Experiments on five graphs show that DeepLinker can not only achieve the state-of-the-art link prediction accuracy, but also acquire the efficient node representations and node centrality ranking as the byproducts. Although the representations are obtained without any supervised node label information, they still perform well on node ranking and node classification tasks.
Guillaume Verdon, Michael Broughton, Jarrod R. McClean et al.
Quantum Neural Networks (QNNs) are a promising variational learning paradigm with applications to near-term quantum processors, however they still face some significant challenges. One such challenge is finding good parameter initialization heuristics that ensure rapid and consistent convergence to local minima of the parameterized quantum circuit landscape. In this work, we train classical neural networks to assist in the quantum learning process, also know as meta-learning, to rapidly find approximate optima in the parameter landscape for several classes of quantum variational algorithms. Specifically, we train classical recurrent neural networks to find approximately optimal parameters within a small number of queries of the cost function for the Quantum Approximate Optimization Algorithm (QAOA) for MaxCut, QAOA for Sherrington-Kirkpatrick Ising model, and for a Variational Quantum Eigensolver for the Hubbard model. By initializing other optimizers at parameter values suggested by the classical neural network, we demonstrate a significant improvement in the total number of optimization iterations required to reach a given accuracy. We further demonstrate that the optimization strategies learned by the neural network generalize well across a range of problem instance sizes. This opens up the possibility of training on small, classically simulatable problem instances, in order to initialize larger, classically intractably simulatable problem instances on quantum devices, thereby significantly reducing the number of required quantum-classical optimization iterations.
Autonomous path planning algorithms are significant to planetary exploration rovers, since relying on commands from Earth will heavily reduce their efficiency of executing exploration missions. This paper proposes a novel learning-based algorithm to deal with global path planning problem for planetary exploration rovers. Specifically, a novel deep convolutional neural network with double branches (DB-CNN) is designed and trained, which can plan path directly from orbital images of planetary surfaces without implementing environment mapping. Moreover, the planning procedure requires no prior knowledge about planetary surface terrains. Finally, experimental results demonstrate that DB-CNN achieves better performance on global path planning and faster convergence during training compared with the existing Value Iteration Network (VIN).