Search Results for author:
Found 26 papers, 10 papers with code
Variational Flow Models: Flowing in Your Style
We introduce "posterior flows" - generalizations of "probability flows" to a broader class of stochastic processes not necessarily diffusion processes - and propose a systematic training-free method to transform the posterior flow of a "linear" stochastic process characterized by the equation Xt = at * X0 + st * X1 into a straight constant-speed (SC) flow, reminiscent of Rectified Flow.
Revisiting the Dataset Bias Problem from a Statistical Perspective
To overcome this challenge, we propose to approximate \frac{1}{p(u|b)} using a biased classifier trained with "bias amplification" losses.
Domain Generalisation via Risk Distribution Matching
Hence, we propose a compelling proposition: Minimising the divergences between risk distributions across training domains leads to robust invariance for DG.
Beyond Surprise: Improving Exploration Through Surprise Novelty
We present a new computing model for intrinsic rewards in reinforcement learning that addresses the limitations of existing surprise-driven explorations.
Memory-Augmented Theory of Mind Network
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.
Causal Inference via Style Transfer for Out-of-distribution Generalisation
A well-known existing causal inference method like back-door adjustment cannot be applied to remove spurious correlations as it requires the observation of confounders.
Face Swapping as A Simple Arithmetic Operation
We propose a novel high-fidelity face swapping method called "Arithmetic Face Swapping" (AFS) that explicitly disentangles the intermediate latent space W+ of a pretrained StyleGAN into the "identity" and "style" subspaces so that a latent code in W+ is the sum of an "identity" code and a "style" code in the corresponding subspaces.
Momentum Adversarial Distillation: Handling Large Distribution Shifts in Data-Free Knowledge Distillation
Since the EMA generator can be considered as an ensemble of the generator's old versions and often undergoes a smaller change in updates compared to the generator, training on its synthetic samples can help the student recall the past knowledge and prevent the student from adapting too quickly to new updates of the generator.
Black-box Few-shot Knowledge Distillation
Traditional KD methods require lots of labeled training samples and a white-box teacher (parameters are accessible) to train a good student.
Defense Against Multi-target Trojan Attacks
To defend against this attack, we first introduce a trigger reverse-engineering mechanism that uses multiple images to recover a variety of potential triggers.
Learning to Constrain Policy Optimization with Virtual Trust Region
We introduce a constrained optimization method for policy gradient reinforcement learning, which uses a virtual trust region to regulate each policy update.
Learning Theory of Mind via Dynamic Traits Attribution
Inspired by the observation that humans often infer the character traits of others, then use it to explain behaviour, we propose a new neural ToM architecture that learns to generate a latent trait vector of an actor from the past trajectories.
Towards Effective and Robust Neural Trojan Defenses via Input Filtering
Trojan attacks on deep neural networks are both dangerous and surreptitious.
Episodic Policy Gradient Training
We introduce a novel training procedure for policy gradient methods wherein episodic memory is used to optimize the hyperparameters of reinforcement learning algorithms on-the-fly.
Semantic Host-free Trojan Attack
In this paper, we propose a novel host-free Trojan attack with triggers that are fixed in the semantic space but not necessarily in the pixel space.
Clustering by Maximizing Mutual Information Across Views
We propose a novel framework for image clustering that incorporates joint representation learning and clustering.
Semi-Supervised Learning with Variational Bayesian Inference and Maximum Uncertainty Regularization
We propose two generic methods for improving semi-supervised learning (SSL).
Unsupervised Anomaly Detection on Temporal Multiway Data
These include the capacity of the compact matrix LSTM to compress noisy data near perfectly, making the strategy of compressing-decompressing data ill-suited for anomaly detection under the noise.
Theory and Evaluation Metrics for Learning Disentangled Representations
We make two theoretical contributions to disentanglement learning by (a) defining precise semantics of disentangled representations, and (b) establishing robust metrics for evaluation.
Graph Transformation Policy Network for Chemical Reaction Prediction
We address a fundamental problem in chemistry known as chemical reaction product prediction.
Attentional Multilabel Learning over Graphs: A Message Passing Approach
GAML regards labels as auxiliary nodes and models them in conjunction with the input graph.
DeepProcess: Supporting business process execution using a MANN-based recommender system
Process-aware Recommender systems can provide critical decision support functionality to aid business process execution by recommending what actions to take next.
Knowledge Graph Embedding with Multiple Relation Projections
Knowledge graphs contain rich relational structures of the world, and thus complement data-driven machine learning in heterogeneous data.
Learning Deep Matrix Representations
We derive several new deep networks: (i) feed-forward nets that map an input matrix into an output matrix, (ii) recurrent nets which map a sequence of input matrices into a sequence of output matrices.
Multilevel Anomaly Detection for Mixed Data
We propose MIXMAD, which stands for MIXed data Multilevel Anomaly Detection, an ensemble method that estimates the sparse regions across multiple levels of abstraction of mixed data.
Outlier Detection on Mixed-Type Data: An Energy-based Approach
We evaluate the proposed method on synthetic and real-world datasets and demonstrate that (a) a proper handling mixed-types is necessary in outlier detection, and (b) free-energy of Mv. RBM is a powerful and efficient outlier scoring method, which is highly competitive against state-of-the-arts.
