Knowledge tracing consists in predicting the performance of some students on new questions given their performance on previous questions, and can be a prior step to optimizing assessment and learning. Deep knowledge tracing (DKT) is a competitive model for knowledge tracing relying on recurrent neural networks, even if some simpler models may match its performance. However, little is known about why DKT works so well. In this paper, we frame deep knowledge tracing as a encoderdecoder architecture. This viewpoint not only allows us to propose better models in terms of performance, simplicity or expressivity but also opens up promising avenues for future research directions. In particular, we show on several small and large datasets that a simpler decoder, with possibly fewer parameters than the one used by DKT, can predict student performance better.
相關內容
We introduced SSR, which utilizes SAM (segment-anything) as a strong regularizer during training, to greatly enhance the robustness of the image encoder for handling various domains. Specifically, given the fact that SAM is pre-trained with a large number of images over the internet, which cover a diverse variety of domains, the feature encoding extracted by the SAM is obviously less dependent on specific domains when compared to the traditional ImageNet pre-trained image encoder. Meanwhile, the ImageNet pre-trained image encoder is still a mature choice of backbone for the semantic segmentation task, especially when the SAM is category-irrelevant. As a result, our SSR provides a simple yet highly effective design. It uses the ImageNet pre-trained image encoder as the backbone, and the intermediate feature of each stage (ie there are 4 stages in MiT-B5) is regularized by SAM during training. After extensive experimentation on GTA5$\rightarrow$Cityscapes, our SSR significantly improved performance over the baseline without introducing any extra inference overhead.
Scilab-RL: A software framework for efficient reinforcement learning and cognitive modeling research
One problem with researching cognitive modeling and reinforcement learning (RL) is that researchers spend too much time on setting up an appropriate computational framework for their experiments. Many open source implementations of current RL algorithms exist, but there is a lack of a modular suite of tools combining different robotic simulators and platforms, data visualization, hyperparameter optimization, and baseline experiments. To address this problem, we present Scilab-RL, a software framework for efficient research in cognitive modeling and reinforcement learning for robotic agents. The framework focuses on goal-conditioned reinforcement learning using Stable Baselines 3 and the OpenAI gym interface. It enables native possibilities for experiment visualizations and hyperparameter optimization. We describe how these features enable researchers to conduct experiments with minimal time effort, thus maximizing research output.
We propose a novel algorithm for the support estimation of partially known Gaussian graphical models that incorporates prior information about the underlying graph. In contrast to classical approaches that provide a point estimate based on a maximum likelihood or a maximum a posteriori criterion using (simple) priors on the precision matrix, we consider a prior on the graph and rely on annealed Langevin diffusion to generate samples from the posterior distribution. Since the Langevin sampler requires access to the score function of the underlying graph prior, we use graph neural networks to effectively estimate the score from a graph dataset (either available beforehand or generated from a known distribution). Numerical experiments demonstrate the benefits of our approach.
We introduce an extension of first-order logic that comes equipped with additional predicates for reasoning about an abstract state. Sequents in the logic comprise a main formula together with pre- and postconditions in the style of Hoare logic, and the axioms and rules of the logic ensure that the assertions about the state compose in the correct way. The main result of the paper is a realizability interpretation of our logic that extracts programs into a mixed functional/imperative language. All programs expressible in this language act on the state in a sequential manner, and we make this intuition precise by interpreting them in a semantic metatheory using the state monad. Our basic framework is very general, and our intention is that it can be instantiated and extended in a variety of different ways. We outline in detail one such extension: A monadic version of Heyting arithmetic with a wellfounded while rule, and conclude by outlining several other directions for future work.
Asymptotic analysis for related inference problems often involves similar steps and proofs. These intermediate results could be shared across problems if each of them is made self-contained and easily identified. However, asymptotic analysis using Taylor expansions is limited for result borrowing because it is a step-to-step procedural approach. This article introduces EEsy, a modular system for estimating finite and infinitely dimensional parameters in related inference problems. It is based on the infinite-dimensional Z-estimation theorem, Donsker and Glivenko-Cantelli preservation theorems, and weight calibration techniques. This article identifies the systematic nature of these tools and consolidates them into one system containing several modules, which can be built, shared, and extended in a modular manner. This change to the structure of method development allows related methods to be developed in parallel and complex problems to be solved collaboratively, expediting the development of new analytical methods. This article considers four related inference problems -- estimating parameters with random sampling, two-phase sampling, auxiliary information incorporation, and model misspecification. We illustrate this modular approach by systematically developing 9 parameter estimators and 18 variance estimators for the four related inference problems regarding semi-parametric additive hazards models. Simulation studies show the obtained asymptotic results for these 27 estimators are valid. In the end, I describe how this system can simplify the use of empirical process theory, a powerful but challenging tool to be adopted by the broad community of methods developers. I discuss challenges and the extension of this system to other inference problems.
In this work, we aim to establish a Bayesian adaptive learning framework by focusing on estimating latent variables in deep neural network (DNN) models. Latent variables indeed encode both transferable distributional information and structural relationships. Thus the distributions of the source latent variables (prior) can be combined with the knowledge learned from the target data (likelihood) to yield the distributions of the target latent variables (posterior) with the goal of addressing acoustic mismatches between training and testing conditions. The prior knowledge transfer is accomplished through Variational Bayes (VB). In addition, we also investigate Maximum a Posteriori (MAP) based Bayesian adaptation. Experimental results on device adaptation in acoustic scene classification show that our proposed approaches can obtain good improvements on target devices, and consistently outperforms other cut-edging algorithms.
Speech foundation models (SFMs) have been benchmarked on many speech processing tasks, often achieving state-of-the-art performance with minimal adaptation. However, the SFM paradigm has been significantly less explored for applications of interest to the speech perception community. In this paper we present a systematic evaluation of 10 SFMs on one such application: Speech intelligibility prediction. We focus on the non-intrusive setup of the Clarity Prediction Challenge 2 (CPC2), where the task is to predict the percentage of words correctly perceived by hearing-impaired listeners from speech-in-noise recordings. We propose a simple method that learns a lightweight specialized prediction head on top of frozen SFMs to approach the problem. Our results reveal statistically significant differences in performance across SFMs. Our method resulted in the winning submission in the CPC2, demonstrating its promise for speech perception applications.
Lately, instruction-based techniques have made significant strides in improving performance in few-shot learning scenarios. They achieve this by bridging the gap between pre-trained language models and fine-tuning for specific downstream tasks. Despite these advancements, the performance of Large Language Models (LLMs) in information extraction tasks like Named Entity Recognition (NER), using prompts or instructions, still falls short of supervised baselines. The reason for this performance gap can be attributed to the fundamental disparity between NER and LLMs. NER is inherently a sequence labeling task, where the model must assign entity-type labels to individual tokens within a sentence. In contrast, LLMs are designed as a text generation task. This distinction between semantic labeling and text generation leads to subpar performance. In this paper, we transform the NER task into a text-generation task that can be readily adapted by LLMs. This involves enhancing source sentences with task-specific instructions and answer choices, allowing for the identification of entities and their types within natural language. We harness the strength of LLMs by integrating supervised learning within them. The goal of this combined strategy is to boost the performance of LLMs in extraction tasks like NER while simultaneously addressing hallucination issues often observed in LLM-generated content. A novel corpus Contract NER comprising seven frequently observed contract categories, encompassing named entities associated with 18 distinct legal entity types is released along with our baseline models. Our models and dataset are available to the community for future research * .
Generative models offer a direct way of modeling complex data. Energy-based models attempt to encode the statistical correlations observed in the data at the level of the Boltzmann weight associated with an energy function in the form of a neural network. We address here the challenge of understanding the physical interpretation of such models. In this study, we propose a simple solution by implementing a direct mapping between the Restricted Boltzmann Machine and an effective Ising spin Hamiltonian. This mapping includes interactions of all possible orders, going beyond the conventional pairwise interactions typically considered in the inverse Ising (or Boltzmann Machine) approach, and allowing the description of complex datasets. Earlier works attempted to achieve this goal, but the proposed mappings were inaccurate for inference applications, did not properly treat the complexity of the problem, or did not provide precise prescriptions for practical application. To validate our method, we performed several controlled inverse numerical experiments in which we trained the RBMs using equilibrium samples of predefined models with local external fields, 2-body and 3-body interactions in different sparse topologies. The results demonstrate the effectiveness of our proposed approach in learning the correct interaction network and pave the way for its application in modeling interesting binary variable datasets. We also evaluate the quality of the inferred model based on different training methods.
The remarkable practical success of deep learning has revealed some major surprises from a theoretical perspective. In particular, simple gradient methods easily find near-optimal solutions to non-convex optimization problems, and despite giving a near-perfect fit to training data without any explicit effort to control model complexity, these methods exhibit excellent predictive accuracy. We conjecture that specific principles underlie these phenomena: that overparametrization allows gradient methods to find interpolating solutions, that these methods implicitly impose regularization, and that overparametrization leads to benign overfitting. We survey recent theoretical progress that provides examples illustrating these principles in simpler settings. We first review classical uniform convergence results and why they fall short of explaining aspects of the behavior of deep learning methods. We give examples of implicit regularization in simple settings, where gradient methods lead to minimal norm functions that perfectly fit the training data. Then we review prediction methods that exhibit benign overfitting, focusing on regression problems with quadratic loss. For these methods, we can decompose the prediction rule into a simple component that is useful for prediction and a spiky component that is useful for overfitting but, in a favorable setting, does not harm prediction accuracy. We focus specifically on the linear regime for neural networks, where the network can be approximated by a linear model. In this regime, we demonstrate the success of gradient flow, and we consider benign overfitting with two-layer networks, giving an exact asymptotic analysis that precisely demonstrates the impact of overparametrization. We conclude by highlighting the key challenges that arise in extending these insights to realistic deep learning settings.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191