相关论文: Ontology Pre-training for Poison Prediction

With the widespread use of information technologies, information networks are becoming increasingly popular to capture complex relationships across various disciplines, such as social networks, citation networks, telecommunication networks,…

Leveraging new data sources is a key step in accelerating the pace of materials design and discovery. To complement the strides in synthesis planning driven by historical, experimental, and computed data, we present an automated method for…

When an autonomous robot learns how to execute actions, it is of interest to know if and when the execution policy can be generalised to variations of the learning scenarios. This can inform the robot about the necessity of additional…

We investigate the task of inserting new concepts extracted from texts into an ontology using language models. We explore an approach with three steps: edge search which is to find a set of candidate locations to insert (i.e., subsumptions…

While next-token prediction (NTP) has been the standard objective for training language models, it often struggles to capture global structure in reasoning tasks. Multi-token prediction (MTP) has recently emerged as a promising alternative,…

In order for artificial neural networks to begin accurately mimicking biological ones, they must be able to adapt to new exigencies without forgetting what they have learned from previous training. Lifelong learning approaches to artificial…

Deep neural networks are widely used for classification. These deep models often suffer from a lack of interpretability -- they are particularly difficult to understand because of their non-linear nature. As a result, neural networks are…

Ontologies provide features like a common vocabulary, reusability, machine-readable content, and also allows for semantic search, facilitate agent interaction and ordering & structuring of knowledge for the Semantic Web (Web 3.0)…

When trained on language data, do transformers learn some arbitrary computation that utilizes the full capacity of the architecture or do they learn a simpler, tree-like computation, hypothesized to underlie compositional meaning systems…

Drug toxicity remains a major challenge in pharmaceutical development. Recent machine learning models have improved in silico toxicity prediction, but their reliance on annotated data and lack of interpretability limit their applicability.…

Tracking entities in procedural language requires understanding the transformations arising from actions on entities as well as those entities' interactions. While self-attention-based pre-trained language encoders like GPT and BERT have…

In recent years, deep learning has made remarkable progress in a wide range of domains, with a particularly notable impact on natural language processing tasks. One of the challenges associated with training deep neural networks in the…

Human reading behavior is tuned to the statistics of natural language: the time it takes human subjects to read a word can be predicted from estimates of the word's probability in context. However, it remains an open question what…

Humans can learn new concepts from a small number of examples by drawing on their inductive biases. These inductive biases have previously been captured by using Bayesian models defined over symbolic hypothesis spaces. Is it possible to…

Understanding toxicity in user conversations is undoubtedly an important problem. Addressing "covert" or implicit cases of toxicity is particularly hard and requires context. Very few previous studies have analysed the influence of…

Pretraining language models directly on web-scale corpora is the de facto paradigm. We study an alternative where the model is initially exposed to abstract structured data to ease the subsequent acquisition of rich semantic knowledge, much…

This overview article makes the case for how topological concepts can enrich research in machine learning. Using the Euler Characteristic Transform (ECT), a geometrical-topological invariant, as a running example, I present different use…

To tackle interpretability in deep learning, we present a novel framework to jointly learn a predictive model and its associated interpretation model. The interpreter provides both local and global interpretability about the predictive…

Inference and prediction are fundamental to the study of complex systems, where network data are often incomplete, inaccurate or obtained indirectly. In this paper, we review recent advances in network sampling and comparison, as well as in…

Humans surpass the cognitive abilities of most other animals in our ability to "chunk" concepts into words, and then combine the words to combine the concepts. In this process, we make "infinite use of finite means", enabling us to learn…