Reinforcement learning and Imitation Learning approaches utilize policy learning strategies that are difficult to generalize well with just a few examples of a task. In this work, we propose a language-conditioned semantic search-based method to produce an online search-based policy from the available demonstration dataset of state-action trajectories. Here we directly acquire actions from the most similar manipulation trajectories found in the dataset. Our approach surpasses the performance of the baselines on the CALVIN benchmark and exhibits strong zero-shot adaptation capabilities. This holds great potential for expanding the use of our online search-based policy approach to tasks typically addressed by Imitation Learning or Reinforcement Learning-based policies.
相關內容
Deep or reinforcement learning (RL) approaches have been adapted as reactive agents to quickly learn and respond with new investment strategies for portfolio management under the highly turbulent financial market environments in recent years. In many cases, due to the very complex correlations among various financial sectors, and the fluctuating trends in different financial markets, a deep or reinforcement learning based agent can be biased in maximising the total returns of the newly formulated investment portfolio while neglecting its potential risks under the turmoil of various market conditions in the global or regional sectors. Accordingly, a multi-agent and self-adaptive framework namely the MASA is proposed in which a sophisticated multi-agent reinforcement learning (RL) approach is adopted through two cooperating and reactive agents to carefully and dynamically balance the trade-off between the overall portfolio returns and their potential risks. Besides, a very flexible and proactive agent as the market observer is integrated into the MASA framework to provide some additional information on the estimated market trends as valuable feedbacks for multi-agent RL approach to quickly adapt to the ever-changing market conditions. The obtained empirical results clearly reveal the potential strengths of our proposed MASA framework based on the multi-agent RL approach against many well-known RL-based approaches on the challenging data sets of the CSI 300, Dow Jones Industrial Average and S&P 500 indexes over the past 10 years. More importantly, our proposed MASA framework shed lights on many possible directions for future investigation.
Due to the data imbalance and the diversity of defects, student-teacher networks (S-T) are favored in unsupervised anomaly detection, which explores the discrepancy in feature representation derived from the knowledge distillation process to recognize anomalies. However, vanilla S-T network is not stable. Employing identical structures to construct the S-T network may weaken the representative discrepancy on anomalies. But using different structures can increase the likelihood of divergent performance on normal data. To address this problem, we propose a novel dual-student knowledge distillation (DSKD) architecture. Different from other S-T networks, we use two student networks a single pre-trained teacher network, where the students have the same scale but inverted structures. This framework can enhance the distillation effect to improve the consistency in recognition of normal data, and simultaneously introduce diversity for anomaly representation. To explore high-dimensional semantic information to capture anomaly clues, we employ two strategies. First, a pyramid matching mode is used to perform knowledge distillation on multi-scale feature maps in the intermediate layers of networks. Second, an interaction is facilitated between the two student networks through a deep feature embedding module, which is inspired by real-world group discussions. In terms of classification, we obtain pixel-wise anomaly segmentation maps by measuring the discrepancy between the output feature maps of the teacher and student networks, from which an anomaly score is computed for sample-wise determination. We evaluate DSKD on three benchmark datasets and probe the effects of internal modules through ablation experiments. The results demonstrate that DSKD can achieve exceptional performance on small models like ResNet18 and effectively improve vanilla S-T networks.
Probability predictions are essential to inform decision making across many fields. Ideally, probability predictions are (i) well calibrated, (ii) accurate, and (iii) bold, i.e., spread out enough to be informative for decision making. However, there is a fundamental tension between calibration and boldness, since calibration metrics can be high when predictions are overly cautious, i.e., non-bold. The purpose of this work is to develop a Bayesian model selection-based approach to assess calibration, and a strategy for boldness-recalibration that enables practitioners to responsibly embolden predictions subject to their required level of calibration. Specifically, we allow the user to pre-specify their desired posterior probability of calibration, then maximally embolden predictions subject to this constraint. We demonstrate the method with a case study on hockey home team win probabilities and then verify the performance of our procedures via simulation. We find that very slight relaxation of calibration probability (e.g., from 0.99 to 0.95) can often substantially embolden predictions when they are well calibrated and accurate (e.g., widening hockey predictions range from .26-.78 to .10-.91).
Continual learning (CL) is the research field that aims to build machine learning models that can accumulate knowledge continuously over different tasks without retraining from scratch. Previous studies have shown that pre-training graph neural networks (GNN) may lead to negative transfer (Hu et al., 2020) after fine-tuning, a setting which is closely related to CL. Thus, we focus on studying GNN in the continual graph learning (CGL) setting. We propose the first continual graph learning benchmark for spatio-temporal graphs and use it to benchmark well-known CGL methods in this novel setting. The benchmark is based on the N-UCLA and NTU-RGB+D datasets for skeleton-based action recognition. Beyond benchmarking for standard performance metrics, we study the class and task-order sensitivity of CGL methods, i.e., the impact of learning order on each class/task's performance, and the architectural sensitivity of CGL methods with backbone GNN at various widths and depths. We reveal that task-order robust methods can still be class-order sensitive and observe results that contradict previous empirical observations on architectural sensitivity in CL.
We propose a reinforcement learning (RL)-based system that would automatically prescribe a hypothetical patient medication that may help the patient with their mental health-related speech disfluency, and adjust the medication and the dosages in response to zero-cost frequent measurement of the fluency of the patient. We demonstrate the components of the system: a module that detects and evaluates speech disfluency on a large dataset we built, and an RL algorithm that automatically finds good combinations of medications. To support the two modules, we collect data on the effect of psychiatric medications for speech disfluency from the literature, and build a plausible patient simulation system. We demonstrate that the RL system is, under some circumstances, able to converge to a good medication regime. We collect and label a dataset of people with possible speech disfluency and demonstrate our methods using that dataset. Our work is a proof of concept: we show that there is promise in the idea of using automatic data collection to address speech disfluency.
Algorithmic paradigms such as divide-and-conquer (D&C) are proposed to guide developers in designing efficient algorithms, but it can still be difficult to apply algorithmic paradigms to practical tasks. To ease the usage of paradigms, many research efforts have been devoted to the automatic application of algorithmic paradigms. However, most existing approaches to this problem rely on syntax-based program transformations and thus put significant restrictions on the original program. In this paper, we study the automatic application of D&C and several similar paradigms, denoted as D&C-like algorithmic paradigms, and aim to remove the restrictions from syntax-based transformations. To achieve this goal, we propose an efficient synthesizer, named AutoLifter, which does not depend on syntax-based transformations. Specifically, the main challenge of applying algorithmic paradigms is from the large scale of the synthesized programs, and AutoLifter addresses this challenge by applying two novel decomposition methods that do not depend on the syntax of the input program, component elimination and variable elimination, to soundly divide the whole problem into simpler subtasks, each synthesizing a sub-program of the final program and being tractable with existing synthesizers. We evaluate AutoLifter on 96 programming tasks related to 6 different algorithmic paradigms. AutoLifter solves 82/96 tasks with an average time cost of 20.17 seconds, significantly outperforming existing approaches.
Personalized federated learning (PFL) has been widely investigated to address the challenge of data heterogeneity, especially when a single generic model is inadequate in satisfying the diverse performance requirements of local clients simultaneously. Existing PFL methods are inherently based on the idea that the relations between the generic global and personalized local models are captured by the similarity of model weights. Such a similarity is primarily based on either partitioning the model architecture into generic versus personalized components, or modeling client relationships via model weights. To better capture similar (yet distinct) generic versus personalized model representations, we propose \textit{spectral distillation}, a novel distillation method based on model spectrum information. Building upon spectral distillation, we also introduce a co-distillation framework that establishes a two-way bridge between generic and personalized model training. Moreover, to utilize the local idle time in conventional PFL, we propose a wait-free local training protocol. Through extensive experiments on multiple datasets over diverse heterogeneous data settings, we demonstrate the outperformance and efficacy of our proposed spectral co-distillation method, as well as our wait-free training protocol.
We study the problem of in-context learning (ICL) with large language models (LLMs) on private datasets. This scenario poses privacy risks, as LLMs may leak or regurgitate the private examples demonstrated in the prompt. We propose a novel algorithm that generates synthetic few-shot demonstrations from the private dataset with formal differential privacy (DP) guarantees, and show empirically that it can achieve effective ICL. We conduct extensive experiments on standard benchmarks and compare our algorithm with non-private ICL and zero-shot solutions. Our results demonstrate that our algorithm can achieve competitive performance with strong privacy levels. These results open up new possibilities for ICL with privacy protection for a broad range of applications.
A mainstream type of current self-supervised learning methods pursues a general-purpose representation that can be well transferred to downstream tasks, typically by optimizing on a given pretext task such as instance discrimination. In this work, we argue that existing pretext tasks inevitably introduce biases into the learned representation, which in turn leads to biased transfer performance on various downstream tasks. To cope with this issue, we propose Maximum Entropy Coding (MEC), a more principled objective that explicitly optimizes on the structure of the representation, so that the learned representation is less biased and thus generalizes better to unseen downstream tasks. Inspired by the principle of maximum entropy in information theory, we hypothesize that a generalizable representation should be the one that admits the maximum entropy among all plausible representations. To make the objective end-to-end trainable, we propose to leverage the minimal coding length in lossy data coding as a computationally tractable surrogate for the entropy, and further derive a scalable reformulation of the objective that allows fast computation. Extensive experiments demonstrate that MEC learns a more generalizable representation than previous methods based on specific pretext tasks. It achieves state-of-the-art performance consistently on various downstream tasks, including not only ImageNet linear probe, but also semi-supervised classification, object detection, instance segmentation, and object tracking. Interestingly, we show that existing batch-wise and feature-wise self-supervised objectives could be seen equivalent to low-order approximations of MEC. Code and pre-trained models are available at //github.com/xinliu20/MEC.
Representation learning on a knowledge graph (KG) is to embed entities and relations of a KG into low-dimensional continuous vector spaces. Early KG embedding methods only pay attention to structured information encoded in triples, which would cause limited performance due to the structure sparseness of KGs. Some recent attempts consider paths information to expand the structure of KGs but lack explainability in the process of obtaining the path representations. In this paper, we propose a novel Rule and Path-based Joint Embedding (RPJE) scheme, which takes full advantage of the explainability and accuracy of logic rules, the generalization of KG embedding as well as the supplementary semantic structure of paths. Specifically, logic rules of different lengths (the number of relations in rule body) in the form of Horn clauses are first mined from the KG and elaborately encoded for representation learning. Then, the rules of length 2 are applied to compose paths accurately while the rules of length 1 are explicitly employed to create semantic associations among relations and constrain relation embeddings. Besides, the confidence level of each rule is also considered in optimization to guarantee the availability of applying the rule to representation learning. Extensive experimental results illustrate that RPJE outperforms other state-of-the-art baselines on KG completion task, which also demonstrate the superiority of utilizing logic rules as well as paths for improving the accuracy and explainability of representation learning.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191