This paper describes an end-to-end solution for the relationship prediction task in heterogeneous, multi-relational graphs. We particularly address two building blocks in the pipeline, namely heterogeneous graph representation learning and negative sampling. Existing message passing-based graph neural networks use edges either for graph traversal and/or selection of message encoding functions. Ignoring the edge semantics could have severe repercussions on the quality of embeddings, especially when dealing with two nodes having multiple relations. Furthermore, the expressivity of the learned representation depends on the quality of negative samples used during training. Although existing hard negative sampling techniques can identify challenging negative relationships for optimization, new techniques are required to control false negatives during training as false negatives could corrupt the learning process. To address these issues, first, we propose RelGNN -- a message passing-based heterogeneous graph attention model. In particular, RelGNN generates the states of different relations and leverages them along with the node states to weigh the messages. RelGNN also adopts a self-attention mechanism to balance the importance of attribute features and topological features for generating the final entity embeddings. Second, we introduce a parameter-free negative sampling technique -- adaptive self-adversarial (ASA) negative sampling. ASA reduces the false-negative rate by leveraging positive relationships to effectively guide the identification of true negative samples. Our experimental evaluation demonstrates that RelGNN optimized by ASA for relationship prediction improves state-of-the-art performance across established benchmarks as well as on a real industrial dataset.

Clever men are more fertile and have more children than others, research has found. The findings suggest that those with higher IQs are considered more attractive by women. In addition, being intelligent leads to status in society and more wealth - extra factors as to why eggheads are considered'a catch'. The research overturns previous findings - that larger families are the preserve of people who are not blessed with higher IQs. Clever men are more fertile and have more children than others, research has found.

Given a pre-trained CNN without any testing samples, this paper proposes a simple yet effective method to diagnose feature representations of the CNN. We aim to discover representation flaws caused by potential dataset bias. More specifically, when the CNN is trained to estimate image attributes, we mine latent relationships between representations of different attributes inside the CNN. Then, we compare the mined attribute relationships with ground-truth attribute relationships to discover the CNN's blind spots and failure modes due to dataset bias. In fact, representation flaws caused by dataset bias cannot be examined by conventional evaluation strategies based on testing images, because testing images may also have a similar bias. Experiments have demonstrated the effectiveness of our method.

How about trying to find any use of the famous Monty Hall problem in a stock index context? First of all, some of you may be confused because neither "Monty Hall problem" nor "Let's make a deal" are familiar to you so I will refresh you what these names are concerned to. Monty Hall was a TV presenter for "Let's make a deal", a famous American show in the sixties. Suppose you're on this game show and you're given the choice of three doors: behind one door there is a prize; behind the others, there is nothing. You pick a door, say number 1, and the host, who knows what's behind the doors, opens another door, say number 3, which results to be empty.