We introduce and analyse a simple probabilistic model of article production and citation behavior that explicitly assumes that there is no decline in citability of a given article over time. It makes predictions about the number and age of items appearing in the reference list of an article. The latter topics have been studied before, but only in the context of data, and to our knowledge no models have been presented. We then perform large-scale analyses of reference list length for a variety of academic disciplines. The results show that our simple model cannot be rejected, and indeed fits the aggregated data on reference lists rather well. Over the last few decades, the relationship between total publications and mean reference list length is linear to a high level of accuracy. Although our model is clearly an oversimplification, it will likely prove useful for further modeling of the scholarly literature. Finally, we connect our work to the large literature on "aging" or "obsolescence" of scholarly publications, and argue that the importance of that area of research is no longer clear, while much of the existing literature is confused and confusing.
相關內容
ACM/IEEE第23屆模型驅動工程語言和系統國際會議，是模型驅動軟件和系統工程的首要會議系列，由ACM-SIGSOFT和IEEE-TCSE支持組織。自1998年以來，模型涵蓋了建模的各個方面，從語言和方法到工具和應用程序。模特的參加者來自不同的背景，包括研究人員、學者、工程師和工業專業人士。MODELS 2019是一個論壇，參與者可以圍繞建模和模型驅動的軟件和系統交流前沿研究成果和創新實踐經驗。今年的版本將為建模社區提供進一步推進建模基礎的機會，并在網絡物理系統、嵌入式系統、社會技術系統、云計算、大數據、機器學習、安全、開源等新興領域提出建模的創新應用以及可持續性。
官網鏈接： ·
MoDELS
·
Performer
·
ImageNet (數據集)
·
Learning
·
We argue that there are many notions of 'similarity' and that models, like humans, should be able to adapt to these dynamically. This contrasts with most representation learning methods, supervised or self-supervised, which learn a fixed embedding function and hence implicitly assume a single notion of similarity. For instance, models trained on ImageNet are biased towards object categories, while a user might prefer the model to focus on colors, textures or specific elements in the scene. In this paper, we propose the GeneCIS ('genesis') benchmark, which measures models' ability to adapt to a range of similarity conditions. Extending prior work, our benchmark is designed for zero-shot evaluation only, and hence considers an open-set of similarity conditions. We find that baselines from powerful CLIP models struggle on GeneCIS and that performance on the benchmark is only weakly correlated with ImageNet accuracy, suggesting that simply scaling existing methods is not fruitful. We further propose a simple, scalable solution based on automatically mining information from existing image-caption datasets. We find our method offers a substantial boost over the baselines on GeneCIS, and further improves zero-shot performance on related image retrieval benchmarks. In fact, though evaluated zero-shot, our model surpasses state-of-the-art supervised models on MIT-States. Project page at //sgvaze.github.io/genecis/.
This work addresses the challenge of providing consistent explanations for predictive models in the presence of model indeterminacy, which arises due to the existence of multiple (nearly) equally well-performing models for a given dataset and task. Despite their similar performance, such models often exhibit inconsistent or even contradictory explanations for their predictions, posing challenges to end users who rely on these models to make critical decisions. Recognizing this issue, we introduce ensemble methods as an approach to enhance the consistency of the explanations provided in these scenarios. Leveraging insights from recent work on neural network loss landscapes and mode connectivity, we devise ensemble strategies to efficiently explore the underspecification set -- the set of models with performance variations resulting solely from changes in the random seed during training. Experiments on five benchmark financial datasets reveal that ensembling can yield significant improvements when it comes to explanation similarity, and demonstrate the potential of existing ensemble methods to explore the underspecification set efficiently. Our findings highlight the importance of considering model indeterminacy when interpreting explanations and showcase the effectiveness of ensembles in enhancing the reliability of explanations in machine learning.
BEIR is a benchmark dataset for zero-shot evaluation of information retrieval models across 18 different domain/task combinations. In recent years, we have witnessed the growing popularity of a representation learning approach to building retrieval models, typically using pretrained transformers in a supervised setting. This naturally begs the question: How effective are these models when presented with queries and documents that differ from the training data? Examples include searching in different domains (e.g., medical or legal text) and with different types of queries (e.g., keywords vs. well-formed questions). While BEIR was designed to answer these questions, our work addresses two shortcomings that prevent the benchmark from achieving its full potential: First, the sophistication of modern neural methods and the complexity of current software infrastructure create barriers to entry for newcomers. To this end, we provide reproducible reference implementations that cover the two main classes of approaches: learned dense and sparse models. Second, there does not exist a single authoritative nexus for reporting the effectiveness of different models on BEIR, which has led to difficulty in comparing different methods. To remedy this, we present an official self-service BEIR leaderboard that provides fair and consistent comparisons of retrieval models. By addressing both shortcomings, our work facilitates future explorations in a range of interesting research questions that BEIR enables.
Data valuation has become an increasingly significant discipline in data science due to the economic value of data. In the context of machine learning (ML), data valuation methods aim to equitably measure the contribution of each data point to the utility of an ML model. One prevalent method is Shapley value, which helps identify data points that are beneficial or detrimental to an ML model. However, traditional Shapley-based data valuation methods may not effectively distinguish between beneficial and detrimental training data points for probabilistic classifiers. In this paper, we propose Probabilistic Shapley (P-Shapley) value by constructing a probability-wise utility function that leverages the predicted class probabilities of probabilistic classifiers rather than binarized prediction results in the traditional Shapley value. We also offer several activation functions for confidence calibration to effectively quantify the marginal contribution of each data point to the probabilistic classifiers. Extensive experiments on four real-world datasets demonstrate the effectiveness of our proposed P-Shapley value in evaluating the importance of data for building a high-usability and trustworthy ML model.
Language has a strong influence on our perceptions of time and rewards. This raises the question of whether large language models, when asked in different languages, show different preferences for rewards over time and if their choices are similar to those of humans. In this study, we analyze the responses of GPT-3.5 (hereafter referred to as GPT) to prompts in multiple languages, exploring preferences between smaller, sooner rewards and larger, later rewards. Our results show that GPT displays greater patience when prompted in languages with weak future tense references (FTR), such as German and Mandarin, compared to languages with strong FTR, like English and French. These findings are consistent with existing literature and suggest a correlation between GPT's choices and the preferences of speakers of these languages. However, further analysis reveals that the preference for earlier or later rewards does not systematically change with reward gaps, indicating a lexicographic preference for earlier payments. While GPT may capture intriguing variations across languages, our findings indicate that the choices made by these models do not correspond to those of human decision-makers.
Knowledge tracing plays a pivotal role in intelligent tutoring systems. This task aims to predict the probability of students answering correctly to specific questions. To do so, knowledge tracing systems should trace the knowledge state of the students by utilizing their problem-solving history and knowledge about the problems. Recent advances in knowledge tracing models have enabled better exploitation of problem solving history. However, knowledge about problems has not been studied, as well compared to students' answering histories. Knowledge tracing algorithms that incorporate knowledge directly are important to settings with limited data or cold starts. Therefore, we consider the problem of utilizing skill-to-skill relation to knowledge tracing. In this work, we introduce expert labeled skill-to-skill relationships. Moreover, we also provide novel methods to construct a knowledge-tracing model to leverage human experts' insight regarding relationships between skills. The results of an extensive experimental analysis show that our method outperformed a baseline Transformer model. Furthermore, we found that the extent of our model's superiority was greater in situations with limited data, which allows a smooth cold start of our model.
Future wireless systems are expected to support mission-critical services demanding higher and higher reliability. In this letter, we dimension the radio resources needed to achieve a given failure probability target for ultra-reliable wireless systems in high interference conditions, assuming a protocol with frequency hopping combined with packet repetitions. We resort to packet erasure channel models and derive the minimum amount of resource units in the case of receiver with and without collision resolution capability, as well as the number of packet repetitions needed for achieving the failure probability target. Analytical results are numerically validated and can be used as a benchmark for realistic system simulations
A well-known boundary observability inequality for the elasticity system establishes that the energy of the system can be estimated from the solution on a sufficiently large part of the boundary for a sufficiently large time. This inequality is relevant in different contexts as the exact boundary controllability, boundary stabilization, or some inverse source problems. Here we show that a corresponding boundary observability inequality for the spectral collocation approximation of the linear elasticity system in a d-dimensional cube also holds, uniformly with respect to the discretization parameter. This property is essential to prove that natural numerical approaches to the previous problems based on replacing the elasticity system by collocation discretization will give successful approximations of the continuous counterparts.
Recommender systems have been widely applied in different real-life scenarios to help us find useful information. Recently, Reinforcement Learning (RL) based recommender systems have become an emerging research topic. It often surpasses traditional recommendation models even most deep learning-based methods, owing to its interactive nature and autonomous learning ability. Nevertheless, there are various challenges of RL when applying in recommender systems. Toward this end, we firstly provide a thorough overview, comparisons, and summarization of RL approaches for five typical recommendation scenarios, following three main categories of RL: value-function, policy search, and Actor-Critic. Then, we systematically analyze the challenges and relevant solutions on the basis of existing literature. Finally, under discussion for open issues of RL and its limitations of recommendation, we highlight some potential research directions in this field.
We describe ACE0, a lightweight platform for evaluating the suitability and viability of AI methods for behaviour discovery in multiagent simulations. Specifically, ACE0 was designed to explore AI methods for multi-agent simulations used in operations research studies related to new technologies such as autonomous aircraft. Simulation environments used in production are often high-fidelity, complex, require significant domain knowledge and as a result have high R&D costs. Minimal and lightweight simulation environments can help researchers and engineers evaluate the viability of new AI technologies for behaviour discovery in a more agile and potentially cost effective manner. In this paper we describe the motivation for the development of ACE0.We provide a technical overview of the system architecture, describe a case study of behaviour discovery in the aerospace domain, and provide a qualitative evaluation of the system. The evaluation includes a brief description of collaborative research projects with academic partners, exploring different AI behaviour discovery methods.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191