Search Results

The challenge in constructing artificial social agents is to enable the ability to adapt to novel agents, and is called zero-shot coordination (ZSC). A promising approach is to train the adaptive agents by interacting with a diverse pool of collaborators,...

Multivariate time series forecasting is essential in various fields, including healthcare and traffic management, but it is a challenging task due to the strong dynamics in both intra-channel relations (temporal patterns within individual ...

Identifying root causes of anomalies in causal processes is vital across disciplines. Once identified, one can isolate the root causes and implement necessary measures to restore the normal operation. Causal processes are often modelled as graphs with ...

The optimistic nature of the Q−learning target leads to an overestimation bias, which is an inherent problem associated with standard Q−learning. Such a bias fails to account for the possibility of low returns, particularly in risky scenarios. ...

Understanding other agents is a key challenge in constructing artificial social agents. Current works focus on centralised training, wherein agents are allowed to know all the information about others and the environmental state during training. In ...

Social reasoning necessitates the capacity of theory of mind (ToM), the ability to contextualise and attribute mental states to others without having access to their internal cognitive structure. Recent machine learning approaches to ToM have demonstrated ...

Data-free Knowledge Distillation (DFKD) has attracted attention recently thanks to its appealing capability of transferring knowledge from a teacher network to a student network without using training data. The main idea is to use a generator to ...

The capacity to achieve out-of-distribution (OOD) generalization is a hallmark of human intelligence and yet remains out of reach for machines. This remarkable capability has been attributed to our abilities to make conceptual abstraction and analogy, ...

Trojan attacks on deep neural networks are both dangerous and surreptitious. Over the past few years, Trojan attacks have advanced from using only a single input-agnostic trigger and targeting only one class to using multiple, input-specific ...

It would be a technological feat to be able to create a system that can hold a meaningful conversation with humans about what they watch. A setup toward that goal is presented as a video dialog task, where the system is asked to generate natural ...$\mathtt{}$$\mathtt{}$$\mathtt{}$$\mathtt{}$

Many high-performance DTA deep learning models have been proposed, but they are mostly black-box and thus lack human interpretability. Explainable AI (XAI) can make DTA models more trustworthy, and allows to distill biological knowledge from the models. ...

Multi-agent reinforcement learning holds the key for solving complex tasks that demand the coordination of learning agents. However, strong coordination often leads to expensive exploration over the exponentially large state-action space. A powerful ...

Machine learning of Theory of Mind (ToM) is essential to build social agents that co-live with humans and other agents. This capacity, once acquired, will help machines infer the mental states of others from observed contextual action trajectories, ...

Episodic control enables sample efficiency in reinforcement learning by recalling past experiences from an episodic memory. We propose a new model-based episodic memory of trajectories addressing current limitations of episodic control. Our memory ...

Process-aware Recommender systems can provide critical decision support functionality to aid business process execution by recommending what actions to take next. Based on recent advances in the field of deep learning, we present a novel memory-...

Video Question Answering (Video QA) challenges modelers in multiple fronts. Modeling video necessitates building not only spatio-temporal models for the dynamic visual channel but also multimodal structures for associated information channels such ...

We introduce a conditional compression problem and propose a fast framework for tackling it. The problem is how to quickly compress a pretrained large neural network into optimal smaller networks given target contexts, e.g., a context involving ...

We propose a framework called HyperVAE for encoding distributions of distributions. When a target distribution is modeled by a VAE, its neural network parameters are sampled from a distribution in the model space modeled by a hyper-level VAE. We ...

Knowledge distillation (KD) is one of the most efficient methods to compress a large deep neural network (called teacher) to a smaller network (called student). Current state-of-the-art KD methods assume that the distributions of training data of ...

The rise of big data and big compute has brought modern neural networks to many walks of digital life, thanks to the relative ease of constructing large models that scale to the real world. Current successes of Transformers and self-supervised ...